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

Dataset: Open Web Text

Neuron 1940 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: 5.0420. Min Range: -5.0420

Max Act: 5.0420. Min Act: -0.1700

Data Index: 5979115 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9500. Min Act: -0.1700

Data Index: 8622095 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9518. Min Act: -0.1700

Data Index: 7328405 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9780. Min Act: -0.1700

Data Index: 8525429 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9701. Min Act: -0.1700

Data Index: 4800926 (Open Web Text)

Max Activating Token Index: 310

Text #5

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9770. Min Act: -0.1700

Data Index: 7684082 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9539. Min Act: -0.1700

Data Index: 2926463 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9753. Min Act: -0.1700

Data Index: 1809226 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9574. Min Act: -0.1700

Data Index: 5979114 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9161. Min Act: -0.1700

Data Index: 6788900 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9301. Min Act: -0.1700

Data Index: 4471526 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9215. Min Act: -0.1700

Data Index: 6367212 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9437. Min Act: -0.1700

Data Index: 8269252 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9356. Min Act: -0.1700

Data Index: 806034 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9310. Min Act: -0.1700

Data Index: 625234 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9183. Min Act: -0.1700

Data Index: 2180559 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9207. Min Act: -0.1700

Data Index: 6815931 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.8859. Min Act: -0.1700

Data Index: 209671 (Open Web Text)

Max Activating Token Index: 236

Text #18

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9386. Min Act: -0.1700

Data Index: 3931789 (Open Web Text)

Max Activating Token Index: 423

Text #19

Max Range: 5.0420. Min Range: -5.0420

Max Act: 4.9051. Min Act: -0.1700

Data Index: 6410634 (Open Web Text)

Max Activating Token Index: 461