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

Dataset: Open Web Text

Neuron 579 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: 3.4274. Min Range: -3.4274

Max Act: 3.4274. Min Act: -0.1700

Data Index: 8622560 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.4229. Min Act: -0.1700

Data Index: 6053071 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.3084. Min Act: -0.1700

Data Index: 2339297 (Open Web Text)

Max Activating Token Index: 595

Text #3

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.3083. Min Act: -0.1700

Data Index: 2842356 (Open Web Text)

Max Activating Token Index: 181

Text #4

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2918. Min Act: -0.1700

Data Index: 2691833 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.3045. Min Act: -0.1700

Data Index: 4797270 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2783. Min Act: -0.1700

Data Index: 6287833 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2946. Min Act: -0.1700

Data Index: 3326647 (Open Web Text)

Max Activating Token Index: 473

Text #8

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2793. Min Act: -0.1700

Data Index: 6131255 (Open Web Text)

Max Activating Token Index: 684

Text #9

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2772. Min Act: -0.1700

Data Index: 3137777 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2518. Min Act: -0.1700

Data Index: 8640439 (Open Web Text)

Max Activating Token Index: 426

Text #11

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2816. Min Act: -0.1700

Data Index: 5357528 (Open Web Text)

Max Activating Token Index: 611

Text #12

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2546. Min Act: -0.1700

Data Index: 4812165 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2539. Min Act: -0.1700

Data Index: 4377389 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2355. Min Act: -0.1700

Data Index: 1651850 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2596. Min Act: -0.1700

Data Index: 21402 (Open Web Text)

Max Activating Token Index: 190

Text #16

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2610. Min Act: -0.1700

Data Index: 7115875 (Open Web Text)

Max Activating Token Index: 880

Text #17

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2093. Min Act: -0.1700

Data Index: 6505672 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2395. Min Act: -0.1700

Data Index: 214697 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 3.4274. Min Range: -3.4274

Max Act: 3.2402. Min Act: -0.1700

Data Index: 5813005 (Open Web Text)

Max Activating Token Index: 779