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

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

Neuron 4987 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: 0.6129. Min Range: -0.6129

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1129592 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.5712. Min Act: -0.0000

Data Index: 551906 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.5158. Min Act: -0.0000

Data Index: 627217 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4975. Min Act: -0.0000

Data Index: 617744 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1214790 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1330283 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1005899 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1196049 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4202. Min Act: -0.0000

Data Index: 731282 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.4080. Min Act: -0.0000

Data Index: 652841 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3781. Min Act: -0.0000

Data Index: 655345 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3950. Min Act: -0.0000

Data Index: 720102 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3856. Min Act: 0.0000

Data Index: 418136 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3602. Min Act: -0.0000

Data Index: 413881 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3785. Min Act: 0.0000

Data Index: 785535 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1262994 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3472. Min Act: -0.0000

Data Index: 516016 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1163800 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1253169 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.6129. Min Range: -0.6129

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1310760 (C4 (Web Text))

Max Activating Token Index: 870