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

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

Neuron 4037 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: 1.3726. Min Range: -1.3726

Max Act: 1.3726. Min Act: -0.0000

Data Index: 453595 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.1549. Min Act: -0.0000

Data Index: 457277 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0581. Min Act: -0.0000

Data Index: 347328 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.1129. Min Act: -0.0000

Data Index: 466005 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0979. Min Act: -0.0000

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0841. Min Act: -0.0000

Data Index: 747830 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1297623 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0095. Min Act: -0.0000

Data Index: 466546 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1001284 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.3726. Min Range: -1.3726

Max Act: 0.9661. Min Act: -0.0000

Data Index: 663615 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1224835 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1183398 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0214. Min Act: -0.0000

Data Index: 196677 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0309. Min Act: -0.0000

Data Index: 840341 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0322. Min Act: -0.0000

Data Index: 208679 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.3726. Min Range: -1.3726

Max Act: 0.9975. Min Act: -0.0000

Data Index: 290132 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 1.3726. Min Range: -1.3726

Max Act: 0.9910. Min Act: -0.0000

Data Index: 152891 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.3726. Min Range: -1.3726

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.3726. Min Range: -1.3726

Max Act: 0.9511. Min Act: -0.0000

Data Index: 374070 (C4 (Web Text))

Max Activating Token Index: 332