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

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

Neuron 2875 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: 1.6038. Min Range: -1.6038

Max Act: 1.6038. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.5491. Min Act: -0.0000

Data Index: 108198 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.5165. Min Act: -0.0000

Data Index: 692818 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.3750. Min Act: -0.0000

Data Index: 652539 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.4555. Min Act: -0.0000

Data Index: 576451 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.4523. Min Act: -0.0000

Data Index: 1056739 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.3172. Min Act: -0.0000

Data Index: 990242 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.3148. Min Act: -0.0000

Data Index: 105774 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.3763. Min Act: -0.0000

Data Index: 450155 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1353838 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.2758. Min Act: -0.0000

Data Index: 235980 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.3397. Min Act: -0.0000

Data Index: 218005 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.1896. Min Act: -0.0000

Data Index: 317127 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1208601 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.2244. Min Act: -0.0000

Data Index: 361556 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.1849. Min Act: -0.0000

Data Index: 372028 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.1993. Min Act: -0.0000

Data Index: 673710 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1013884 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1008175 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.6038. Min Range: -1.6038

Max Act: 1.1374. Min Act: -0.0000

Data Index: 672739 (C4 (Web Text))

Max Activating Token Index: 798