Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6490. Min Range: -4.6490

Max Act: 4.6490. Min Act: -0.0000

Data Index: 140230 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 4.6490. Min Range: -4.6490

Max Act: 4.4887. Min Act: -0.0000

Data Index: 385856 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 4.6490. Min Range: -4.6490

Max Act: 4.2661. Min Act: -0.0000

Data Index: 677678 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.7191. Min Act: -0.0000

Data Index: 812664 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.8650. Min Act: -0.0000

Data Index: 1133849 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.7639. Min Act: -0.0000

Data Index: 620785 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.6650. Min Act: -0.0000

Data Index: 681973 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.4827. Min Act: -0.0000

Data Index: 454589 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.3188. Min Act: -0.0000

Data Index: 447941 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.4028. Min Act: -0.0000

Data Index: 1185951 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.5238. Min Act: -0.0000

Data Index: 983123 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.3461. Min Act: -0.0000

Data Index: 929065 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.3374. Min Act: -0.0000

Data Index: 85533 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.3574. Min Act: -0.0000

Data Index: 92053 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.1578. Min Act: -0.0000

Data Index: 656015 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.4765. Min Act: -0.0000

Data Index: 578368 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.3247. Min Act: -0.0000

Data Index: 292788 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.3208. Min Act: -0.0000

Data Index: 921773 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.4896. Min Act: -0.0000

Data Index: 1296456 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 4.6490. Min Range: -4.6490

Max Act: 3.2792. Min Act: -0.0000

Data Index: 978027 (C4 (Web Text))

Max Activating Token Index: 139