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

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

Neuron 1688 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4671. Min Act: -0.0000

Data Index: 342418 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4451. Min Act: -0.0000

Data Index: 133928 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4099. Min Act: -0.0000

Data Index: 112280 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1007387 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3953. Min Act: 0.0000

Data Index: 258441 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3577. Min Act: -0.0000

Data Index: 346598 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3732. Min Act: -0.0000

Data Index: 943810 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.4190. Min Act: -0.0000

Data Index: 865641 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1241658 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1467800 (Python Code)

Max Activating Token Index: 790

Text #10

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3097. Min Act: -0.0000

Data Index: 288605 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3376. Min Act: -0.0000

Data Index: 357563 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1092563 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1571773 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1124931 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3428. Min Act: -0.0000

Data Index: 373780 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1262195 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1148292 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.3432. Min Act: -0.0000

Data Index: 995051 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.4671. Min Range: -0.4671

Max Act: 0.2888. Min Act: -0.0000

Data Index: 289191 (C4 (Web Text))

Max Activating Token Index: 255