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

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

Neuron 3828 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.7038. Min Act: -0.0000

Data Index: 152479 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6092. Min Act: -0.0000

Data Index: 602724 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6823. Min Act: -0.0000

Data Index: 257937 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6301. Min Act: -0.0000

Data Index: 431333 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1343335 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5262. Min Act: -0.0000

Data Index: 498008 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5208. Min Act: -0.0000

Data Index: 446506 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4381. Min Act: -0.0000

Data Index: 518900 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4688. Min Act: -0.0000

Data Index: 406557 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1229822 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4099. Min Act: -0.0000

Data Index: 272969 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4265. Min Act: -0.0000

Data Index: 447375 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4372. Min Act: -0.0000

Data Index: 813686 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4291. Min Act: -0.0000

Data Index: 842862 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4419. Min Act: -0.0000

Data Index: 228485 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4241. Min Act: -0.0000

Data Index: 38444 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.3903. Min Act: -0.0000

Data Index: 143525 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4119. Min Act: -0.0000

Data Index: 25781 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1209717 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4113. Min Act: -0.0000

Data Index: 958365 (C4 (Web Text))

Max Activating Token Index: 982