< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.6097. Min Act: -0.1700

Data Index: 8080057 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5794. Min Act: -0.1700

Data Index: 6690144 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5960. Min Act: -0.1700

Data Index: 7488750 (Open Web Text)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5770. Min Act: -0.1700

Data Index: 5649126 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5257. Min Act: -0.1700

Data Index: 1789923 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5362. Min Act: -0.1700

Data Index: 720158 (Open Web Text)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5232. Min Act: -0.1700

Data Index: 5664088 (Open Web Text)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5368. Min Act: -0.1700

Data Index: 2870214 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4998. Min Act: -0.1700

Data Index: 6563800 (Open Web Text)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5176. Min Act: -0.1700

Data Index: 3913165 (Open Web Text)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4935. Min Act: -0.1700

Data Index: 6315194 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5019. Min Act: -0.1700

Data Index: 2334791 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.5013. Min Act: -0.1700

Data Index: 226134 (Open Web Text)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4647. Min Act: -0.1700

Data Index: 2833006 (Open Web Text)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4935. Min Act: -0.1700

Data Index: 6061423 (Open Web Text)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4689. Min Act: -0.1700

Data Index: 7886423 (Open Web Text)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4711. Min Act: -0.1700

Data Index: 1420405 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4646. Min Act: -0.1700

Data Index: 1240249 (Open Web Text)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4734. Min Act: -0.1700

Data Index: 5137497 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6097. Min Range: -2.6097

Max Act: 2.4626. Min Act: -0.1700

Data Index: 1249063 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #19