Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0004

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0290. Min Act: -0.0004

Data Index: 528073 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0004

Data Index: 565331 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0273. Min Act: -0.0004

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1003613 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0272. Min Act: -0.0004

Data Index: 294195 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0257. Min Act: -0.0004

Data Index: 1284253 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1004139 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0239. Min Act: -0.0004

Data Index: 32833 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0256. Min Act: -0.0004

Data Index: 1010925 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0238. Min Act: -0.0004

Data Index: 87266 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0004

Data Index: 805978 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0262. Min Act: -0.0004

Data Index: 538850 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0256. Min Act: -0.0004

Data Index: 246049 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1212109 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1045636 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0004

Data Index: 854636 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0247. Min Act: -0.0004

Data Index: 1330036 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1234973 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0251. Min Act: -0.0004

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 349