< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2596 in Layer 3

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: 2.7237. Min Range: -2.7237

Max Act: 2.7237. Min Act: -0.1700

Data Index: 6622813 (Open Web Text)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.7206. Min Act: -0.1700

Data Index: 6381982 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.7138. Min Act: -0.1700

Data Index: 4020566 (Open Web Text)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.6601. Min Act: -0.1700

Data Index: 7732896 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.6381. Min Act: -0.1700

Data Index: 7017026 (Open Web Text)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.6278. Min Act: -0.1700

Data Index: 6330550 (Open Web Text)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.6320. Min Act: -0.1700

Data Index: 626743 (Open Web Text)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.6050. Min Act: -0.1700

Data Index: 8102813 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.6133. Min Act: -0.1700

Data Index: 3313707 (Open Web Text)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5992. Min Act: -0.1700

Data Index: 5526403 (Open Web Text)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5804. Min Act: -0.1700

Data Index: 7380861 (Open Web Text)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5866. Min Act: -0.1700

Data Index: 7301975 (Open Web Text)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5590. Min Act: -0.1700

Data Index: 1626214 (Open Web Text)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5764. Min Act: -0.1700

Data Index: 7924822 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5899. Min Act: -0.1700

Data Index: 6809275 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5669. Min Act: -0.1700

Data Index: 6981381 (Open Web Text)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5742. Min Act: -0.1700

Data Index: 3277139 (Open Web Text)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5663. Min Act: -0.1700

Data Index: 5426552 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5635. Min Act: -0.1700

Data Index: 5426555 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7237. Min Range: -2.7237

Max Act: 2.5429. Min Act: -0.1700

Data Index: 5909667 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #19