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

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

Neuron 4046 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4142. Min Range: -2.4142

Max Act: 2.4142. Min Act: -0.0000

Data Index: 632960 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 2.4142. Min Range: -2.4142

Max Act: 2.2198. Min Act: -0.0000

Data Index: 1205450 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.5209. Min Act: -0.0000

Data Index: 421082 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.6651. Min Act: -0.0000

Data Index: 118243 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.6566. Min Act: -0.0000

Data Index: 607006 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.5369. Min Act: -0.0000

Data Index: 107479 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.3411. Min Act: -0.0000

Data Index: 2045 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.3255. Min Act: -0.0000

Data Index: 827197 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.3040. Min Act: -0.0000

Data Index: 758540 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1144927 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1575. Min Act: -0.0000

Data Index: 162849 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1680. Min Act: -0.0000

Data Index: 644092 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1280. Min Act: -0.0000

Data Index: 655496 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1968. Min Act: -0.0000

Data Index: 942017 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1333427 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1336. Min Act: -0.0000

Data Index: 620711 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1213. Min Act: -0.0000

Data Index: 101383 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1334. Min Act: -0.0000

Data Index: 53020 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.0406. Min Act: 0.0000

Data Index: 1294818 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 2.4142. Min Range: -2.4142

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1250182 (C4 (Web Text))

Max Activating Token Index: 402