Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0262. Min Act: -0.0006

Data Index: 430717 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0260. Min Act: -0.0006

Data Index: 438834 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0257. Min Act: -0.0006

Data Index: 633379 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0232. Min Act: -0.0006

Data Index: 972255 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1177381 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0237. Min Act: -0.0006

Data Index: 137793 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0241. Min Act: -0.0006

Data Index: 212523 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0219. Min Act: -0.0006

Data Index: 110221 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0239. Min Act: -0.0006

Data Index: 392940 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0232. Min Act: -0.0006

Data Index: 757636 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0231. Min Act: -0.0006

Data Index: 197599 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0254. Min Act: -0.0006

Data Index: 424548 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0244. Min Act: -0.0006

Data Index: 166742 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0220. Min Act: -0.0006

Data Index: 533802 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1212023 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0233. Min Act: -0.0006

Data Index: 610741 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0235. Min Act: -0.0006

Data Index: 114815 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0219. Min Act: -0.0006

Data Index: 384707 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0234. Min Act: -0.0006

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0224. Min Act: -0.0006

Data Index: 554248 (C4 (Web Text))

Max Activating Token Index: 630