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

Dataset: Open Web Text

Neuron 551 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: 3.5302. Min Range: -3.5302

Max Act: 3.5302. Min Act: -0.1700

Data Index: 2544010 (Open Web Text)

Max Activating Token Index: 297

Text #1

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3892. Min Act: -0.1700

Data Index: 4378194 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3325. Min Act: -0.1700

Data Index: 1632113 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3190. Min Act: -0.1700

Data Index: 6819366 (Open Web Text)

Max Activating Token Index: 731

Text #4

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2851. Min Act: -0.1700

Data Index: 2848222 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2823. Min Act: -0.1700

Data Index: 3824125 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2923. Min Act: -0.1700

Data Index: 8532911 (Open Web Text)

Max Activating Token Index: 388

Text #7

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2720. Min Act: -0.1700

Data Index: 8096385 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2964. Min Act: -0.1700

Data Index: 120152 (Open Web Text)

Max Activating Token Index: 420

Text #9

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2725. Min Act: -0.1700

Data Index: 4927522 (Open Web Text)

Max Activating Token Index: 298

Text #10

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2705. Min Act: -0.1700

Data Index: 3264198 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2725. Min Act: -0.1700

Data Index: 2243471 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2636. Min Act: -0.1700

Data Index: 5144353 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2382. Min Act: -0.1700

Data Index: 2899355 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1252674 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2047. Min Act: -0.1700

Data Index: 2554854 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2471. Min Act: -0.1700

Data Index: 2700268 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2006. Min Act: -0.1700

Data Index: 8421884 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.2061. Min Act: -0.1700

Data Index: 4864994 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.1848. Min Act: -0.1700

Data Index: 6115378 (Open Web Text)

Max Activating Token Index: 411