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

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

Neuron 4205 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: 2.5560. Min Range: -2.5560

Max Act: 2.5560. Min Act: -0.0000

Data Index: 296636 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.4216. Min Act: -0.0000

Data Index: 1278221 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.2561. Min Act: -0.0000

Data Index: 953540 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.1411. Min Act: -0.0000

Data Index: 112251 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.1178. Min Act: -0.0000

Data Index: 401888 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.0834. Min Act: -0.0000

Data Index: 738823 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.9627. Min Act: -0.0000

Data Index: 95591 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.0571. Min Act: -0.0000

Data Index: 169030 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.1666. Min Act: -0.0000

Data Index: 240124 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.0356. Min Act: -0.0000

Data Index: 223711 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.9366. Min Act: -0.0000

Data Index: 303635 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.0017. Min Act: -0.0000

Data Index: 870360 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.9629. Min Act: -0.0000

Data Index: 1277883 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.8579. Min Act: -0.0000

Data Index: 727720 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.0572. Min Act: -0.0000

Data Index: 278583 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.8518. Min Act: -0.0000

Data Index: 64710 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.9274. Min Act: -0.0000

Data Index: 892673 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.7038. Min Act: -0.0000

Data Index: 345003 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 2.5560. Min Range: -2.5560

Max Act: 2.0214. Min Act: -0.0000

Data Index: 1199018 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 2.5560. Min Range: -2.5560

Max Act: 1.9925. Min Act: -0.0000

Data Index: 1113914 (C4 (Web Text))

Max Activating Token Index: 126