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

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

Neuron 5113 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.5091. Min Act: -0.0000

Data Index: 157310 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.2016. Min Act: -0.0000

Data Index: 152580 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1017923 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.1191. Min Act: -0.0000

Data Index: 255893 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0488. Min Act: -0.0000

Data Index: 331377 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0811. Min Act: -0.0000

Data Index: 509262 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9636. Min Act: -0.0000

Data Index: 985693 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0852. Min Act: 0.0000

Data Index: 1315786 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1204412 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9849. Min Act: -0.0000

Data Index: 1063837 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0024. Min Act: -0.0000

Data Index: 593970 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9698. Min Act: -0.0000

Data Index: 980006 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9253. Min Act: 0.0000

Data Index: 344922 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1119619 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.5091. Min Range: -1.5091

Max Act: 1.0011. Min Act: 0.0001

Data Index: 1268920 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9198. Min Act: -0.0000

Data Index: 48110 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9223. Min Act: -0.0000

Data Index: 157290 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.9247. Min Act: -0.0000

Data Index: 817407 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.5091. Min Range: -1.5091

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1019038 (C4 (Web Text))

Max Activating Token Index: 79