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

Dataset: Open Web Text

Neuron 217 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: 3.7142. Min Range: -3.7142

Max Act: 3.7142. Min Act: -0.1700

Data Index: 4677300 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5439. Min Act: -0.1700

Data Index: 2395552 (Open Web Text)

Max Activating Token Index: 721

Text #2

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5367. Min Act: -0.1700

Data Index: 6390172 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5409. Min Act: -0.1700

Data Index: 532713 (Open Web Text)

Max Activating Token Index: 307

Text #4

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5250. Min Act: -0.1700

Data Index: 1254308 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5148. Min Act: -0.1700

Data Index: 8208510 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5015. Min Act: -0.1700

Data Index: 4084163 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5126. Min Act: -0.1700

Data Index: 4737571 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4967. Min Act: -0.1700

Data Index: 4087168 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4754. Min Act: -0.1700

Data Index: 6418270 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4728. Min Act: -0.1700

Data Index: 2265955 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4807. Min Act: -0.1700

Data Index: 1805383 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4689. Min Act: -0.1700

Data Index: 7154 (Open Web Text)

Max Activating Token Index: 828

Text #13

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.5083. Min Act: -0.1700

Data Index: 4361198 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4760. Min Act: -0.1700

Data Index: 7867136 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4731. Min Act: -0.1700

Data Index: 8156927 (Open Web Text)

Max Activating Token Index: 768

Text #16

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4556. Min Act: -0.1700

Data Index: 6753692 (Open Web Text)

Max Activating Token Index: 269

Text #17

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4615. Min Act: -0.1700

Data Index: 2112931 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.4356. Min Act: -0.1700

Data Index: 4217205 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 3.7142. Min Range: -3.7142

Max Act: 3.3991. Min Act: -0.1700

Data Index: 2034160 (Open Web Text)

Max Activating Token Index: 765