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

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

Neuron 736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.5688. Min Act: -0.0000

Data Index: 789249 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1280491 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1179311 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1078181 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1857. Min Act: -0.0000

Data Index: 503792 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2160. Min Act: -0.0000

Data Index: 289089 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2075. Min Act: -0.0000

Data Index: 691633 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1231. Min Act: -0.0000

Data Index: 182561 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1238846 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1589. Min Act: -0.0000

Data Index: 823151 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1104636 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1384. Min Act: -0.0000

Data Index: 336563 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1134955 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0874. Min Act: -0.0000

Data Index: 49167 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1040608 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1250. Min Act: -0.0000

Data Index: 381280 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0608. Min Act: -0.0000

Data Index: 159314 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0540. Min Act: -0.0000

Data Index: 502031 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1213. Min Act: -0.0000

Data Index: 84494 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0545. Min Act: -0.0000

Data Index: 532667 (C4 (Web Text))

Max Activating Token Index: 154