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

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

Neuron 3131 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: 6.0170. Min Range: -6.0170

Max Act: 5.7906. Min Act: -0.0000

Data Index: 998767 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 6.0170. Min Range: -6.0170

Max Act: 6.0170. Min Act: -0.0000

Data Index: 882960 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.4419. Min Act: -0.0000

Data Index: 135576 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.6424. Min Act: -0.0000

Data Index: 230622 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.7518. Min Act: -0.0000

Data Index: 123184 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.5496. Min Act: -0.0000

Data Index: 1211006 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.9169. Min Act: -0.0000

Data Index: 736894 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.5191. Min Act: -0.0000

Data Index: 385283 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.6845. Min Act: -0.0000

Data Index: 724198 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.6100. Min Act: -0.0000

Data Index: 188890 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.4627. Min Act: -0.0000

Data Index: 678957 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.5705. Min Act: -0.0000

Data Index: 997091 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.5046. Min Act: -0.0000

Data Index: 368183 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.2994. Min Act: -0.0000

Data Index: 61144 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.7079. Min Act: -0.0000

Data Index: 811526 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.3312. Min Act: -0.0000

Data Index: 704456 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.5823. Min Act: -0.0000

Data Index: 548805 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.2179. Min Act: -0.0000

Data Index: 504458 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.5628. Min Act: -0.0000

Data Index: 531802 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 6.0170. Min Range: -6.0170

Max Act: 5.7256. Min Act: -0.0000

Data Index: 303736 (C4 (Web Text))

Max Activating Token Index: 724