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

Dataset: Open Web Text

Neuron 2742 in Layer 6

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: 4.6417. Min Range: -4.6417

Max Act: 4.6417. Min Act: -0.1700

Data Index: 7422335 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3885. Min Act: -0.1700

Data Index: 4831133 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3396. Min Act: -0.1700

Data Index: 5295661 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3474. Min Act: -0.1700

Data Index: 3782678 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3364. Min Act: -0.1700

Data Index: 166965 (Open Web Text)

Max Activating Token Index: 749

Text #5

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3306. Min Act: -0.1700

Data Index: 7102960 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3496. Min Act: -0.1700

Data Index: 6695994 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3356. Min Act: -0.1700

Data Index: 4102964 (Open Web Text)

Max Activating Token Index: 372

Text #8

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3263. Min Act: -0.1700

Data Index: 7590793 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3164. Min Act: -0.1700

Data Index: 918467 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3453. Min Act: -0.1700

Data Index: 2273737 (Open Web Text)

Max Activating Token Index: 334

Text #11

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3260. Min Act: -0.1700

Data Index: 1761978 (Open Web Text)

Max Activating Token Index: 685

Text #12

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.2887. Min Act: -0.1700

Data Index: 4828576 (Open Web Text)

Max Activating Token Index: 903

Text #13

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3024. Min Act: -0.1700

Data Index: 866635 (Open Web Text)

Max Activating Token Index: 311

Text #14

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3074. Min Act: -0.1700

Data Index: 6089057 (Open Web Text)

Max Activating Token Index: 509

Text #15

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3029. Min Act: -0.1700

Data Index: 6317051 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3038. Min Act: -0.1700

Data Index: 6370503 (Open Web Text)

Max Activating Token Index: 191

Text #17

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3082. Min Act: -0.1700

Data Index: 4245744 (Open Web Text)

Max Activating Token Index: 239

Text #18

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3104. Min Act: -0.1700

Data Index: 1858351 (Open Web Text)

Max Activating Token Index: 309

Text #19

Max Range: 4.6417. Min Range: -4.6417

Max Act: 4.3144. Min Act: -0.1700

Data Index: 7173073 (Open Web Text)

Max Activating Token Index: 707