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

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

Neuron 109 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5216. Min Range: -7.5216

Max Act: 7.5216. Min Act: -0.0000

Data Index: 1310843 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 7.5216. Min Range: -7.5216

Max Act: 7.0655. Min Act: -0.0000

Data Index: 853322 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 7.5216. Min Range: -7.5216

Max Act: 7.2330. Min Act: -0.0000

Data Index: 766761 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 7.5216. Min Range: -7.5216

Max Act: 7.2630. Min Act: -0.0000

Data Index: 206620 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 7.5216. Min Range: -7.5216

Max Act: 6.6925. Min Act: -0.0000

Data Index: 1007834 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 7.5216. Min Range: -7.5216

Max Act: 6.7879. Min Act: -0.0000

Data Index: 456638 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 7.5216. Min Range: -7.5216

Max Act: 6.9269. Min Act: -0.0000

Data Index: 1213801 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 7.5216. Min Range: -7.5216

Max Act: 6.1439. Min Act: -0.0000

Data Index: 274688 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 7.5216. Min Range: -7.5216

Max Act: 6.1342. Min Act: -0.0000

Data Index: 1205671 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.9836. Min Act: -0.0000

Data Index: 517365 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.7754. Min Act: -0.0000

Data Index: 140889 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.6242. Min Act: -0.0000

Data Index: 77534 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.4336. Min Act: -0.0000

Data Index: 1172380 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.6170. Min Act: -0.0000

Data Index: 754738 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.2991. Min Act: -0.0000

Data Index: 951298 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.2763. Min Act: -0.0000

Data Index: 1295927 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.2203. Min Act: -0.0000

Data Index: 516200 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.1982. Min Act: -0.0000

Data Index: 1186925 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 7.5216. Min Range: -7.5216

Max Act: 5.0838. Min Act: -0.0000

Data Index: 1017667 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 7.5216. Min Range: -7.5216

Max Act: 4.9367. Min Act: -0.0000

Data Index: 307652 (C4 (Web Text))

Max Activating Token Index: 145