Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 252 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.4472. Min Act: -0.0001

Data Index: 713449 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1280721 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2503. Min Act: -0.0000

Data Index: 441902 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2398. Min Act: -0.0000

Data Index: 499789 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2459. Min Act: -0.0000

Data Index: 441692 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2260. Min Act: -0.0000

Data Index: 638456 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2383. Min Act: -0.0000

Data Index: 979399 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2382. Min Act: -0.0001

Data Index: 591333 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1328998 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2282. Min Act: -0.0000

Data Index: 749193 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2143. Min Act: -0.0001

Data Index: 708149 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2120. Min Act: -0.0001

Data Index: 414026 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2189. Min Act: -0.0001

Data Index: 794058 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2107. Min Act: -0.0001

Data Index: 962458 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1160689 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2249. Min Act: -0.0001

Data Index: 372394 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2156. Min Act: -0.0001

Data Index: 379782 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2159. Min Act: -0.0000

Data Index: 126864 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2315. Min Act: -0.0000

Data Index: 452793 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.4472. Min Range: -0.4472

Max Act: 0.2057. Min Act: -0.0000

Data Index: 540576 (C4 (Web Text))

Max Activating Token Index: 688