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

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

Neuron 640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.6667. Min Act: -0.0000

Data Index: 457712 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.7319. Min Act: -0.0000

Data Index: 739719 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1279780 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5132. Min Act: -0.0000

Data Index: 467576 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5044. Min Act: -0.0000

Data Index: 975716 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5847. Min Act: -0.0000

Data Index: 59041 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4019. Min Act: -0.0000

Data Index: 891503 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1303934 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5131. Min Act: -0.0000

Data Index: 816986 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1107626 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4825. Min Act: -0.0000

Data Index: 595303 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.5178. Min Act: -0.0000

Data Index: 175288 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1259065 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4336. Min Act: -0.0000

Data Index: 570996 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4333. Min Act: -0.0000

Data Index: 751686 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3889. Min Act: -0.0000

Data Index: 894246 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4698. Min Act: -0.0000

Data Index: 65231 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3821. Min Act: -0.0000

Data Index: 991905 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1253108 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.7319. Min Range: -1.7319

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1035064 (C4 (Web Text))

Max Activating Token Index: 991