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

Dataset: Open Web Text

Neuron 1873 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: 3.6994. Min Range: -3.6994

Max Act: 3.6994. Min Act: -0.1700

Data Index: 4002478 (Open Web Text)

Max Activating Token Index: 249

Text #1

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.6693. Min Act: -0.1700

Data Index: 3448039 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.6034. Min Act: -0.1700

Data Index: 8425524 (Open Web Text)

Max Activating Token Index: 169

Text #3

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5745. Min Act: -0.1700

Data Index: 4104573 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5111. Min Act: -0.1700

Data Index: 613583 (Open Web Text)

Max Activating Token Index: 908

Text #5

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5296. Min Act: -0.1700

Data Index: 3260928 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5110. Min Act: -0.1700

Data Index: 1384333 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5152. Min Act: -0.1700

Data Index: 1451907 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4725. Min Act: -0.1700

Data Index: 102274 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4698. Min Act: -0.1700

Data Index: 1258019 (Open Web Text)

Max Activating Token Index: 365

Text #10

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4538. Min Act: -0.1700

Data Index: 652830 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4772. Min Act: -0.1700

Data Index: 3918758 (Open Web Text)

Max Activating Token Index: 446

Text #12

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4761. Min Act: -0.1700

Data Index: 536788 (Open Web Text)

Max Activating Token Index: 117

Text #13

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4272. Min Act: -0.1700

Data Index: 2984081 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4431. Min Act: -0.1700

Data Index: 4959264 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4418. Min Act: -0.1700

Data Index: 8073777 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4398. Min Act: -0.1700

Data Index: 1963542 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4169. Min Act: -0.1700

Data Index: 2586260 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4324. Min Act: -0.1700

Data Index: 5891068 (Open Web Text)

Max Activating Token Index: 237

Text #19

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4291. Min Act: -0.1700

Data Index: 322366 (Open Web Text)

Max Activating Token Index: 234