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

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

Neuron 558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.3478. Min Act: -0.0000

Data Index: 524760 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.5490. Min Act: -0.0000

Data Index: 1129100 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.3277. Min Act: -0.0000

Data Index: 618343 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.1094. Min Act: -0.0000

Data Index: 472717 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.9046. Min Act: -0.0000

Data Index: 583014 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.0099. Min Act: -0.0000

Data Index: 774653 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.0672. Min Act: -0.0000

Data Index: 814908 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 2.5490. Min Range: -2.5490

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1155513 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.8695. Min Act: -0.0000

Data Index: 356671 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.8554. Min Act: -0.0000

Data Index: 1260919 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1032161 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.7243. Min Act: -0.0000

Data Index: 176630 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.8153. Min Act: -0.0000

Data Index: 1013122 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.8013. Min Act: -0.0000

Data Index: 582465 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1053164 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.7596. Min Act: -0.0000

Data Index: 1113446 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.6425. Min Act: -0.0000

Data Index: 261505 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.7637. Min Act: -0.0000

Data Index: 666163 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.7533. Min Act: -0.0000

Data Index: 1102928 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 2.5490. Min Range: -2.5490

Max Act: 1.6578. Min Act: -0.0000

Data Index: 1007045 (C4 (Web Text))

Max Activating Token Index: 1002