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

Dataset: Open Web Text

Neuron 531 in Layer 1

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: 1.9222. Min Range: -1.9222

Max Act: 1.9222. Min Act: -0.1699

Data Index: 1142948 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.9055. Min Act: -0.1700

Data Index: 3117351 (Open Web Text)

Max Activating Token Index: 953

Text #2

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8806. Min Act: -0.1700

Data Index: 2696514 (Open Web Text)

Max Activating Token Index: 377

Text #3

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8620. Min Act: -0.1700

Data Index: 2962194 (Open Web Text)

Max Activating Token Index: 325

Text #4

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8622. Min Act: -0.1700

Data Index: 2615547 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8439. Min Act: -0.1700

Data Index: 1455907 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8390. Min Act: -0.1700

Data Index: 1363669 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8345. Min Act: -0.1700

Data Index: 5958272 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8306. Min Act: -0.1700

Data Index: 7765169 (Open Web Text)

Max Activating Token Index: 448

Text #9

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8311. Min Act: -0.1700

Data Index: 7784526 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8366. Min Act: -0.1700

Data Index: 3369818 (Open Web Text)

Max Activating Token Index: 863

Text #11

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8318. Min Act: -0.1698

Data Index: 5795337 (Open Web Text)

Max Activating Token Index: 646

Text #12

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8186. Min Act: -0.1700

Data Index: 3683369 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8095. Min Act: -0.1700

Data Index: 2834600 (Open Web Text)

Max Activating Token Index: 773

Text #14

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8181. Min Act: -0.1700

Data Index: 5409661 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8098. Min Act: -0.1700

Data Index: 4116613 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8111. Min Act: -0.1700

Data Index: 8832166 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8144. Min Act: -0.1700

Data Index: 6423684 (Open Web Text)

Max Activating Token Index: 915

Text #18

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8022. Min Act: -0.1700

Data Index: 4250594 (Open Web Text)

Max Activating Token Index: 730

Text #19

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8055. Min Act: -0.1700

Data Index: 454862 (Open Web Text)

Max Activating Token Index: 718