< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2591 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.6309. Min Act: -0.1700

Data Index: 3106066 (Open Web Text)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.6082. Min Act: -0.1700

Data Index: 3881559 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.5729. Min Act: -0.1700

Data Index: 6641669 (Open Web Text)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.5181. Min Act: -0.1700

Data Index: 6425256 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.5024. Min Act: -0.1700

Data Index: 8070210 (Open Web Text)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4707. Min Act: -0.1700

Data Index: 996098 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4385. Min Act: -0.1700

Data Index: 7859726 (Open Web Text)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4583. Min Act: -0.1700

Data Index: 8504570 (Open Web Text)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4530. Min Act: -0.1700

Data Index: 8711942 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4296. Min Act: -0.1700

Data Index: 7430474 (Open Web Text)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4148. Min Act: -0.1700

Data Index: 31671 (Open Web Text)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4354. Min Act: -0.1700

Data Index: 1973147 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4060. Min Act: -0.1700

Data Index: 3914186 (Open Web Text)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4139. Min Act: -0.1700

Data Index: 2138371 (Open Web Text)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4089. Min Act: -0.1700

Data Index: 7314387 (Open Web Text)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4144. Min Act: -0.1700

Data Index: 7532919 (Open Web Text)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.3732. Min Act: -0.1700

Data Index: 5767130 (Open Web Text)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.3837. Min Act: -0.1700

Data Index: 6249714 (Open Web Text)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.4023. Min Act: -0.1700

Data Index: 3222316 (Open Web Text)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6309. Min Range: -2.6309

Max Act: 2.3585. Min Act: -0.1700

Data Index: 5859824 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #19