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

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

Neuron 4895 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.5678. Min Act: -0.0001

Data Index: 1141283 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1090561 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4590. Min Act: -0.0001

Data Index: 538018 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4549. Min Act: -0.0001

Data Index: 651139 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4256. Min Act: -0.0001

Data Index: 567635 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4356. Min Act: -0.0001

Data Index: 1190058 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4024. Min Act: -0.0001

Data Index: 843278 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1146555 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3880. Min Act: -0.0000

Data Index: 761812 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3849. Min Act: -0.0001

Data Index: 835999 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3889. Min Act: -0.0001

Data Index: 294456 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3909. Min Act: -0.0001

Data Index: 697081 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3788. Min Act: -0.0001

Data Index: 122875 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3686. Min Act: -0.0000

Data Index: 44964 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3717. Min Act: -0.0001

Data Index: 916498 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3374. Min Act: -0.0000

Data Index: 66991 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1188835 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1148862 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3294. Min Act: -0.0001

Data Index: 1191150 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1048276 (C4 (Web Text))

Max Activating Token Index: 73