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

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

Neuron 4676 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: 0.8168. Min Range: -0.8168

Max Act: 0.8168. Min Act: -0.0000

Data Index: 288497 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7324. Min Act: -0.0000

Data Index: 166819 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7571. Min Act: -0.0000

Data Index: 739334 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7282. Min Act: -0.0000

Data Index: 434437 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1354729 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6551. Min Act: -0.0000

Data Index: 122898 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6471. Min Act: -0.0000

Data Index: 901171 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6563. Min Act: -0.0000

Data Index: 185435 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6177. Min Act: -0.0000

Data Index: 756265 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6402. Min Act: -0.0000

Data Index: 57723 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6439. Min Act: -0.0000

Data Index: 151638 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6159. Min Act: -0.0000

Data Index: 971110 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6290. Min Act: -0.0000

Data Index: 411178 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1056555 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5765. Min Act: -0.0000

Data Index: 938468 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5920. Min Act: -0.0000

Data Index: 788860 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5809. Min Act: -0.0000

Data Index: 89817 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5950. Min Act: -0.0000

Data Index: 499668 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1352016 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5578. Min Act: -0.0000

Data Index: 411660 (C4 (Web Text))

Max Activating Token Index: 984