Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 765 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.5145. Min Act: -0.0001

Data Index: 1082094 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4747. Min Act: -0.0001

Data Index: 709140 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4840. Min Act: -0.0000

Data Index: 792388 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4823. Min Act: -0.0000

Data Index: 143961 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4249. Min Act: -0.0001

Data Index: 773239 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4260. Min Act: -0.0001

Data Index: 329206 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4237. Min Act: -0.0000

Data Index: 104825 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4200. Min Act: -0.0001

Data Index: 87761 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1033014 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3980. Min Act: -0.0001

Data Index: 716328 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3738. Min Act: -0.0001

Data Index: 773651 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1074906 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1341657 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3499. Min Act: -0.0001

Data Index: 526897 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3838. Min Act: -0.0001

Data Index: 129616 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3388. Min Act: -0.0001

Data Index: 454067 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3422. Min Act: -0.0001

Data Index: 769946 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3593. Min Act: -0.0000

Data Index: 531482 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3305. Min Act: -0.0001

Data Index: 173602 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3664. Min Act: -0.0001

Data Index: 345978 (C4 (Web Text))

Max Activating Token Index: 170