Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3510 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0003

Data Index: 836370 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0366. Min Act: -0.0002

Data Index: 933392 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1598431 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0341. Min Act: -0.0003

Data Index: 470002 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0329. Min Act: -0.0002

Data Index: 424427 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0318. Min Act: -0.0002

Data Index: 638757 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1570002 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1211130 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1239267 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0299. Min Act: -0.0003

Data Index: 431916 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0307. Min Act: -0.0003

Data Index: 611377 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1268675 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0288. Min Act: -0.0002

Data Index: 790998 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0289. Min Act: -0.0003

Data Index: 345721 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0281. Min Act: -0.0002

Data Index: 208841 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0285. Min Act: -0.0003

Data Index: 297154 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1294446 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0272. Min Act: -0.0003

Data Index: 604247 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0275. Min Act: -0.0002

Data Index: 793905 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0280. Min Act: -0.0002

Data Index: 68534 (C4 (Web Text))

Max Activating Token Index: 740