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

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

Neuron 669 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: 0.8581. Min Range: -0.8581

Max Act: 0.8301. Min Act: -0.0000

Data Index: 471165 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7858. Min Act: -0.0000

Data Index: 716902 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1068112 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1464229 (Python Code)

Max Activating Token Index: 495

Text #4

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7853. Min Act: -0.0000

Data Index: 185455 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1088369 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1018821 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7856. Min Act: -0.0000

Data Index: 276933 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1230911 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6733. Min Act: -0.0000

Data Index: 495224 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7283. Min Act: -0.0000

Data Index: 514315 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7039. Min Act: -0.0000

Data Index: 815638 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7131. Min Act: -0.0000

Data Index: 470927 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7316. Min Act: -0.0000

Data Index: 763983 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7251. Min Act: -0.0000

Data Index: 472695 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1010556 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1465481 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1642354 (Python Code)

Max Activating Token Index: 674

Text #18

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6374. Min Act: -0.0000

Data Index: 488093 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6378. Min Act: -0.0000

Data Index: 993636 (C4 (Web Text))

Max Activating Token Index: 410