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

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

Neuron 3582 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: 2.1645. Min Range: -2.1645

Max Act: 1.9591. Min Act: -0.0000

Data Index: 581575 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 2.1645. Min Range: -2.1645

Max Act: 2.1645. Min Act: -0.0000

Data Index: 260859 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.7237. Min Act: -0.0000

Data Index: 684679 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.5076. Min Act: -0.0000

Data Index: 983354 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.3796. Min Act: -0.0000

Data Index: 231071 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.3027. Min Act: -0.0000

Data Index: 286289 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.3527. Min Act: -0.0000

Data Index: 888360 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.3041. Min Act: -0.0000

Data Index: 147266 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1157204 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2787. Min Act: -0.0000

Data Index: 1348592 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2504. Min Act: -0.0000

Data Index: 296341 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2839. Min Act: -0.0000

Data Index: 107036 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2187. Min Act: -0.0000

Data Index: 951346 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2000. Min Act: -0.0000

Data Index: 496527 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.2767. Min Act: -0.0000

Data Index: 385262 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.1279. Min Act: -0.0000

Data Index: 383272 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.1774. Min Act: -0.0000

Data Index: 776795 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 2.1645. Min Range: -2.1645

Max Act: 1.1802. Min Act: -0.0000

Data Index: 185660 (C4 (Web Text))

Max Activating Token Index: 763