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

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

Neuron 1846 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: 1.9396. Min Range: -1.9396

Max Act: 1.9396. Min Act: -0.0000

Data Index: 384053 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.8369. Min Act: -0.0000

Data Index: 399172 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.7766. Min Act: -0.0000

Data Index: 605878 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.6656. Min Act: -0.0000

Data Index: 415575 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.6506. Min Act: -0.0000

Data Index: 1289805 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.5793. Min Act: -0.0000

Data Index: 556206 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.5706. Min Act: -0.0000

Data Index: 229954 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.5307. Min Act: -0.0000

Data Index: 949793 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1317125 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.3696. Min Act: -0.0000

Data Index: 370440 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.4583. Min Act: -0.0000

Data Index: 1208558 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.3604. Min Act: -0.0000

Data Index: 7723 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.5347. Min Act: -0.0000

Data Index: 734072 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.3577. Min Act: -0.0000

Data Index: 662335 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.4170. Min Act: -0.0000

Data Index: 344924 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1157525 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.4104. Min Act: -0.0000

Data Index: 67986 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.4033. Min Act: -0.0000

Data Index: 325270 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.3099. Min Act: -0.0000

Data Index: 56205 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.9396. Min Range: -1.9396

Max Act: 1.3678. Min Act: -0.0000

Data Index: 434446 (C4 (Web Text))

Max Activating Token Index: 358