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

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

Neuron 629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.9760. Min Act: -0.0000

Data Index: 524138 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8502. Min Act: -0.0000

Data Index: 340531 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7966. Min Act: -0.0000

Data Index: 135064 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8114. Min Act: -0.0000

Data Index: 590522 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8085. Min Act: -0.0000

Data Index: 945128 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1085180 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7883. Min Act: -0.0000

Data Index: 210362 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.8225. Min Act: -0.0000

Data Index: 378066 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7747. Min Act: -0.0000

Data Index: 226140 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7685. Min Act: -0.0000

Data Index: 557446 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7873. Min Act: -0.0000

Data Index: 12514 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7577. Min Act: -0.0000

Data Index: 170801 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7643. Min Act: -0.0000

Data Index: 224891 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7565. Min Act: -0.0000

Data Index: 599165 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7699. Min Act: -0.0000

Data Index: 284346 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7650. Min Act: -0.0000

Data Index: 203321 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7156. Min Act: -0.0000

Data Index: 142416 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7274. Min Act: -0.0000

Data Index: 439657 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7266. Min Act: -0.0000

Data Index: 531157 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.9760. Min Range: -0.9760

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1054436 (C4 (Web Text))

Max Activating Token Index: 465