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

Dataset: Open Web Text

Neuron 1642 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: 3.4197. Min Range: -3.4197

Max Act: 3.4197. Min Act: -0.1700

Data Index: 5697470 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3988. Min Act: -0.1700

Data Index: 7035926 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3793. Min Act: -0.1700

Data Index: 2238758 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3757. Min Act: -0.1700

Data Index: 250644 (Open Web Text)

Max Activating Token Index: 491

Text #4

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3757. Min Act: -0.1700

Data Index: 689190 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3624. Min Act: -0.1700

Data Index: 859513 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3411. Min Act: -0.1700

Data Index: 3066558 (Open Web Text)

Max Activating Token Index: 335

Text #7

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3338. Min Act: -0.1700

Data Index: 4003768 (Open Web Text)

Max Activating Token Index: 592

Text #8

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3470. Min Act: -0.1700

Data Index: 1826492 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3292. Min Act: -0.1700

Data Index: 3188660 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3294. Min Act: -0.1700

Data Index: 8682816 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3250. Min Act: -0.1700

Data Index: 2852996 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.2845. Min Act: -0.1700

Data Index: 5733584 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3073. Min Act: -0.1700

Data Index: 2928409 (Open Web Text)

Max Activating Token Index: 959

Text #14

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.2910. Min Act: -0.1700

Data Index: 6360169 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.3084. Min Act: -0.1700

Data Index: 4053357 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.2869. Min Act: -0.1700

Data Index: 2953006 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.2890. Min Act: -0.1700

Data Index: 555272 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.2772. Min Act: -0.1700

Data Index: 471936 (Open Web Text)

Max Activating Token Index: 191

Text #19

Max Range: 3.4197. Min Range: -3.4197

Max Act: 3.2852. Min Act: -0.1700

Data Index: 4170185 (Open Web Text)

Max Activating Token Index: 175