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

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

Neuron 2905 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: 0.8108. Min Range: -0.8108

Max Act: 0.8065. Min Act: -0.0000

Data Index: 856893 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.8108. Min Act: -0.0000

Data Index: 600628 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7360. Min Act: -0.0000

Data Index: 200954 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7446. Min Act: -0.0000

Data Index: 329013 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1314579 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1134719 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6586. Min Act: -0.0000

Data Index: 383415 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6454. Min Act: -0.0000

Data Index: 808037 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6172. Min Act: -0.0000

Data Index: 255002 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6326. Min Act: -0.0000

Data Index: 86566 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6091. Min Act: -0.0000

Data Index: 858271 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6392. Min Act: -0.0000

Data Index: 386849 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6279. Min Act: -0.0000

Data Index: 442244 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6464. Min Act: -0.0000

Data Index: 177711 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1191668 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6179. Min Act: -0.0000

Data Index: 851002 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6139. Min Act: -0.0000

Data Index: 115899 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6093. Min Act: -0.0000

Data Index: 504183 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1189427 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.5937. Min Act: -0.0000

Data Index: 228579 (C4 (Web Text))

Max Activating Token Index: 16