Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3960 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.8766. Min Act: -0.0000

Data Index: 184623 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.7829. Min Act: -0.0000

Data Index: 343221 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.6488. Min Act: -0.0000

Data Index: 479743 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.2212. Min Act: -0.0000

Data Index: 457270 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.1677. Min Act: 0.0000

Data Index: 716319 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.2845. Min Act: -0.0000

Data Index: 576141 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1239067 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.9591. Min Act: -0.0000

Data Index: 185171 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.9306. Min Act: -0.0000

Data Index: 326040 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.7317. Min Act: -0.0000

Data Index: 1009398 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 2.8766. Min Range: -2.8766

Max Act: 2.0191. Min Act: -0.0000

Data Index: 24250 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.8605. Min Act: -0.0000

Data Index: 135090 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.8321. Min Act: -0.0000

Data Index: 865406 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.7189. Min Act: -0.0000

Data Index: 33291 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.7092. Min Act: -0.0000

Data Index: 579243 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.6904. Min Act: 0.0000

Data Index: 306604 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.6969. Min Act: -0.0000

Data Index: 1277339 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.7793. Min Act: -0.0000

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.6808. Min Act: -0.0000

Data Index: 156893 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 2.8766. Min Range: -2.8766

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1112323 (C4 (Web Text))

Max Activating Token Index: 719