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

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

Neuron 5651 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2966. Min Range: -6.2966

Max Act: 6.2966. Min Act: -0.0000

Data Index: 432219 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 6.2966. Min Range: -6.2966

Max Act: 6.0812. Min Act: -0.0000

Data Index: 530429 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 6.2966. Min Range: -6.2966

Max Act: 6.0172. Min Act: -0.0000

Data Index: 721929 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 6.2966. Min Range: -6.2966

Max Act: 6.2573. Min Act: -0.0000

Data Index: 1277925 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.7619. Min Act: -0.0000

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.8786. Min Act: -0.0000

Data Index: 968648 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 6.2966. Min Range: -6.2966

Max Act: 6.0303. Min Act: -0.0000

Data Index: 946930 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.6580. Min Act: -0.0000

Data Index: 505264 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.3192. Min Act: -0.0000

Data Index: 504949 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 6.2966. Min Range: -6.2966

Max Act: 6.0441. Min Act: -0.0000

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.4758. Min Act: -0.0000

Data Index: 1319725 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.9089. Min Act: -0.0000

Data Index: 569536 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.6252. Min Act: -0.0000

Data Index: 99388 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.4871. Min Act: -0.0000

Data Index: 816275 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.8489. Min Act: -0.0000

Data Index: 78917 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.8041. Min Act: -0.0000

Data Index: 1238185 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.6685. Min Act: -0.0000

Data Index: 765474 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.4798. Min Act: -0.0000

Data Index: 187040 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.5039. Min Act: -0.0000

Data Index: 876998 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 6.2966. Min Range: -6.2966

Max Act: 5.3055. Min Act: -0.0000

Data Index: 265590 (C4 (Web Text))

Max Activating Token Index: 285