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

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

Neuron 4765 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.7132. Min Act: -0.0000

Data Index: 653938 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1354454 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4863. Min Act: -0.0000

Data Index: 963456 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4832. Min Act: -0.0000

Data Index: 604746 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4836. Min Act: -0.0000

Data Index: 13815 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4362. Min Act: -0.0000

Data Index: 666810 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4202. Min Act: -0.0000

Data Index: 554415 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4042. Min Act: -0.0000

Data Index: 676236 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3687. Min Act: -0.0000

Data Index: 961852 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3677. Min Act: -0.0000

Data Index: 552460 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3246. Min Act: -0.0000

Data Index: 939621 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3780. Min Act: -0.0000

Data Index: 958298 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3570. Min Act: -0.0000

Data Index: 206076 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3702. Min Act: -0.0000

Data Index: 343765 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3573. Min Act: -0.0000

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1236809 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3217. Min Act: -0.0000

Data Index: 759114 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1220013 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.3022. Min Act: -0.0000

Data Index: 654209 (C4 (Web Text))

Max Activating Token Index: 284