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

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

Neuron 860 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.5010. Min Act: -0.0001

Data Index: 1174287 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1085123 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3326. Min Act: -0.0001

Data Index: 62556 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1269256 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3237. Min Act: -0.0001

Data Index: 74165 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3532. Min Act: -0.0000

Data Index: 107016 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3428. Min Act: -0.0001

Data Index: 1156167 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3104. Min Act: -0.0001

Data Index: 363876 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1316905 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2971. Min Act: -0.0000

Data Index: 450172 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3159. Min Act: -0.0000

Data Index: 339567 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2959. Min Act: -0.0001

Data Index: 1444239 (Python Code)

Max Activating Token Index: 378

Text #12

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2943. Min Act: -0.0001

Data Index: 918746 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2940. Min Act: -0.0001

Data Index: 98588 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1139819 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2919. Min Act: -0.0001

Data Index: 438268 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1611671 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3039. Min Act: -0.0000

Data Index: 255852 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3030. Min Act: -0.0001

Data Index: 314351 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1122858 (C4 (Web Text))

Max Activating Token Index: 349