Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5972 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.4807. Min Act: -0.0000

Data Index: 1064311 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.5405. Min Act: -0.0000

Data Index: 888630 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.3743. Min Act: -0.0000

Data Index: 681464 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1357304 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.3255. Min Act: -0.0000

Data Index: 565483 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.2876. Min Act: -0.0000

Data Index: 567105 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.4139. Min Act: -0.0000

Data Index: 262038 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.3869. Min Act: -0.0000

Data Index: 396125 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.2718. Min Act: -0.0000

Data Index: 1147048 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1636100 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.2142. Min Act: -0.0000

Data Index: 1110393 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.2192. Min Act: -0.0000

Data Index: 1016356 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.6242. Min Act: -0.0000

Data Index: 364985 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.1384. Min Act: -0.0000

Data Index: 569990 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.1083. Min Act: -0.0000

Data Index: 161887 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 2.5405. Min Range: -2.5405

Max Act: 2.0956. Min Act: -0.0000

Data Index: 1289974 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.9765. Min Act: -0.0000

Data Index: 963188 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.8412. Min Act: -0.0000

Data Index: 393827 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.8345. Min Act: -0.0000

Data Index: 1125321 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 2.5405. Min Range: -2.5405

Max Act: 1.9323. Min Act: -0.0000

Data Index: 193942 (C4 (Web Text))

Max Activating Token Index: 975