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

Dataset: Open Web Text

Neuron 1431 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: 3.9975. Min Range: -3.9975

Max Act: 3.9774. Min Act: -0.1700

Data Index: 8798500 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9975. Min Act: -0.1700

Data Index: 7206999 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9621. Min Act: -0.1700

Data Index: 8091873 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9530. Min Act: -0.1700

Data Index: 4545128 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9736. Min Act: -0.1700

Data Index: 4628172 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9196. Min Act: -0.1700

Data Index: 872391 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9108. Min Act: -0.1700

Data Index: 7168760 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9326. Min Act: -0.1700

Data Index: 5683661 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9184. Min Act: -0.1700

Data Index: 8798502 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8972. Min Act: -0.1700

Data Index: 7527762 (Open Web Text)

Max Activating Token Index: 977

Text #10

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9134. Min Act: -0.1700

Data Index: 3354491 (Open Web Text)

Max Activating Token Index: 587

Text #11

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8934. Min Act: -0.1700

Data Index: 5683664 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8941. Min Act: -0.1700

Data Index: 8518700 (Open Web Text)

Max Activating Token Index: 242

Text #13

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8921. Min Act: -0.1700

Data Index: 8518702 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.9100. Min Act: -0.1700

Data Index: 4442069 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8661. Min Act: -0.1700

Data Index: 3944264 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8517. Min Act: -0.1700

Data Index: 8518698 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8752. Min Act: -0.1700

Data Index: 3551223 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8671. Min Act: -0.1700

Data Index: 7527764 (Open Web Text)

Max Activating Token Index: 265

Text #19

Max Range: 3.9975. Min Range: -3.9975

Max Act: 3.8685. Min Act: -0.1700

Data Index: 3944269 (Open Web Text)

Max Activating Token Index: 966