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

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

Neuron 2968 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0107. Min Range: -1.0107

Max Act: 1.0107. Min Act: -0.0000

Data Index: 302377 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8146. Min Act: -0.0000

Data Index: 500214 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7710. Min Act: -0.0000

Data Index: 578321 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1187754 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7587. Min Act: -0.0000

Data Index: 662506 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7254. Min Act: -0.0000

Data Index: 399251 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7012. Min Act: -0.0000

Data Index: 301851 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7340. Min Act: -0.0000

Data Index: 78514 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7022. Min Act: -0.0000

Data Index: 545969 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6992. Min Act: -0.0000

Data Index: 840172 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7141. Min Act: -0.0000

Data Index: 246064 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7075. Min Act: -0.0000

Data Index: 313216 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.7550. Min Act: -0.0000

Data Index: 150601 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6693. Min Act: -0.0000

Data Index: 367079 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6790. Min Act: -0.0000

Data Index: 106095 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1162612 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6398. Min Act: -0.0000

Data Index: 423913 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1073466 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6722. Min Act: -0.0000

Data Index: 929430 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.0107. Min Range: -1.0107

Max Act: 0.6602. Min Act: -0.0000

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 766