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

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

Neuron 4629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0000

Data Index: 836557 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0513. Min Act: -0.0000

Data Index: 980335 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0542. Min Act: -0.0000

Data Index: 56281 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0503. Min Act: -0.0000

Data Index: 864535 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0476. Min Act: -0.0000

Data Index: 102222 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0412. Min Act: -0.0000

Data Index: 145347 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0399. Min Act: -0.0000

Data Index: 852034 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0370. Min Act: -0.0000

Data Index: 705520 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0340. Min Act: -0.0000

Data Index: 738778 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0346. Min Act: -0.0000

Data Index: 770340 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0355. Min Act: -0.0000

Data Index: 94713 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0317. Min Act: -0.0000

Data Index: 722123 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0336. Min Act: -0.0000

Data Index: 540267 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1206797 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0318. Min Act: -0.0000

Data Index: 161220 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0315. Min Act: -0.0000

Data Index: 360302 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1206826 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1096771 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1031336 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0293. Min Act: -0.0000

Data Index: 800234 (C4 (Web Text))

Max Activating Token Index: 906