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

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

Neuron 329 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.9522. Min Act: -0.0000

Data Index: 152542 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.7154. Min Act: -0.0000

Data Index: 212353 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6458. Min Act: -0.0000

Data Index: 416510 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6109. Min Act: -0.0000

Data Index: 641936 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6375. Min Act: -0.0000

Data Index: 228587 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5899. Min Act: -0.0000

Data Index: 77143 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5602. Min Act: -0.0000

Data Index: 867884 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5914. Min Act: -0.0000

Data Index: 258271 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5543. Min Act: -0.0000

Data Index: 488616 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1101561 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.6131. Min Act: -0.0000

Data Index: 516709 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5662. Min Act: -0.0000

Data Index: 396719 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5061. Min Act: -0.0000

Data Index: 624964 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5589. Min Act: -0.0000

Data Index: 519464 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5316. Min Act: -0.0000

Data Index: 375314 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1287930 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5257. Min Act: -0.0000

Data Index: 878227 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1341763 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1075970 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.9522. Min Range: -0.9522

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1132905 (C4 (Web Text))

Max Activating Token Index: 885