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

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

Neuron 2496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3220. Min Range: -2.3220

Max Act: 2.3220. Min Act: -0.0000

Data Index: 320961 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 2.3220. Min Range: -2.3220

Max Act: 2.2358. Min Act: -0.0000

Data Index: 1033155 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 2.3220. Min Range: -2.3220

Max Act: 2.0432. Min Act: -0.0000

Data Index: 608495 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.9323. Min Act: -0.0000

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.9185. Min Act: -0.0000

Data Index: 124509 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.8577. Min Act: -0.0000

Data Index: 362423 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.8898. Min Act: -0.0000

Data Index: 1219512 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.7624. Min Act: -0.0000

Data Index: 930189 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.7601. Min Act: -0.0000

Data Index: 575078 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.7364. Min Act: -0.0000

Data Index: 649585 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.7849. Min Act: -0.0000

Data Index: 1192248 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.8085. Min Act: -0.0000

Data Index: 576430 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.8273. Min Act: -0.0000

Data Index: 894845 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1199941 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.6731. Min Act: -0.0000

Data Index: 235032 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.6205. Min Act: -0.0000

Data Index: 1344974 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.6312. Min Act: -0.0000

Data Index: 805817 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.6538. Min Act: -0.0000

Data Index: 313300 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.4103. Min Act: -0.0000

Data Index: 802466 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 2.3220. Min Range: -2.3220

Max Act: 1.5432. Min Act: -0.0000

Data Index: 474596 (C4 (Web Text))

Max Activating Token Index: 978