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

Dataset: Open Web Text

Neuron 755 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: 4.5262. Min Range: -4.5262

Max Act: 4.5262. Min Act: -0.1700

Data Index: 6663599 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.5069. Min Act: -0.1700

Data Index: 6663566 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.4837. Min Act: -0.1700

Data Index: 6663574 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.4789. Min Act: -0.1700

Data Index: 2649751 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3907. Min Act: -0.1700

Data Index: 8656384 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.4212. Min Act: -0.1700

Data Index: 1595978 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.4148. Min Act: -0.1700

Data Index: 43112 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3708. Min Act: -0.1700

Data Index: 4069089 (Open Web Text)

Max Activating Token Index: 270

Text #8

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3783. Min Act: -0.1700

Data Index: 1445708 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3301. Min Act: -0.1700

Data Index: 5416792 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3860. Min Act: -0.1700

Data Index: 4229369 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3179. Min Act: -0.1700

Data Index: 5840767 (Open Web Text)

Max Activating Token Index: 494

Text #12

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3589. Min Act: -0.1700

Data Index: 2124472 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3638. Min Act: -0.1700

Data Index: 6994876 (Open Web Text)

Max Activating Token Index: 511

Text #14

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3295. Min Act: -0.1700

Data Index: 6564469 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3369. Min Act: -0.1700

Data Index: 6437410 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3274. Min Act: -0.1700

Data Index: 6437407 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3070. Min Act: -0.1700

Data Index: 557280 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3551. Min Act: -0.1700

Data Index: 5839100 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 4.5262. Min Range: -4.5262

Max Act: 4.3286. Min Act: -0.1700

Data Index: 3044026 (Open Web Text)

Max Activating Token Index: 448