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

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

Neuron 2309 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.7855. Min Act: -0.0000

Data Index: 776047 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6545. Min Act: -0.0000

Data Index: 105402 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6843. Min Act: -0.0000

Data Index: 513003 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6420. Min Act: -0.0000

Data Index: 888849 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.6544. Min Act: -0.0000

Data Index: 527314 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5485. Min Act: -0.0000

Data Index: 408673 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1235717 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5573. Min Act: -0.0000

Data Index: 97172 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5889. Min Act: -0.0000

Data Index: 215062 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1303265 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5376. Min Act: -0.0000

Data Index: 5754 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1186135 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5375. Min Act: -0.0000

Data Index: 580167 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5378. Min Act: -0.0000

Data Index: 100745 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1028538 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1101560 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1199641 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.4790. Min Act: -0.0000

Data Index: 125669 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5042. Min Act: -0.0000

Data Index: 339732 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.7855. Min Range: -0.7855

Max Act: 0.5062. Min Act: -0.0000

Data Index: 988834 (C4 (Web Text))

Max Activating Token Index: 110