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

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

Neuron 2678 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: 1.3244. Min Range: -1.3244

Max Act: 1.3244. Min Act: -0.0000

Data Index: 864454 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.2186. Min Act: -0.0000

Data Index: 866862 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.2108. Min Act: -0.0000

Data Index: 731565 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1005973 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.0916. Min Act: -0.0000

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.0889. Min Act: -0.0000

Data Index: 381342 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9979. Min Act: -0.0000

Data Index: 736111 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9830. Min Act: -0.0000

Data Index: 435580 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9875. Min Act: -0.0000

Data Index: 770104 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9568. Min Act: -0.0000

Data Index: 823978 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8746. Min Act: -0.0000

Data Index: 66871 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9556. Min Act: -0.0000

Data Index: 45699 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8982. Min Act: -0.0000

Data Index: 508721 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 1.3244. Min Range: -1.3244

Max Act: 1.0099. Min Act: -0.0000

Data Index: 350889 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9153. Min Act: -0.0000

Data Index: 420820 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9265. Min Act: -0.0000

Data Index: 974239 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1088648 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9332. Min Act: -0.0000

Data Index: 964625 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1015602 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.3244. Min Range: -1.3244

Max Act: 0.9618. Min Act: -0.0000

Data Index: 807390 (C4 (Web Text))

Max Activating Token Index: 690