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

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

Neuron 85 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: 0.6859. Min Range: -0.6859

Max Act: 0.6859. Min Act: -0.0000

Data Index: 673424 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.6492. Min Act: -0.0000

Data Index: 291106 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.6316. Min Act: -0.0000

Data Index: 895647 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1178237 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1157429 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5817. Min Act: -0.0000

Data Index: 694979 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5806. Min Act: -0.0000

Data Index: 939313 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5482. Min Act: -0.0000

Data Index: 523081 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5640. Min Act: -0.0000

Data Index: 167231 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5594. Min Act: -0.0000

Data Index: 802188 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5760. Min Act: -0.0000

Data Index: 311539 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5564. Min Act: -0.0000

Data Index: 949919 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1318022 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1136603 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5302. Min Act: -0.0000

Data Index: 505123 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5558. Min Act: -0.0000

Data Index: 672114 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5370. Min Act: -0.0000

Data Index: 942344 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5471. Min Act: -0.0000

Data Index: 889845 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5005. Min Act: 0.0000

Data Index: 230340 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.6859. Min Range: -0.6859

Max Act: 0.5326. Min Act: -0.0000

Data Index: 48908 (C4 (Web Text))

Max Activating Token Index: 11