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

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

Neuron 4112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.8272. Min Act: -0.0001

Data Index: 57358 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7999. Min Act: -0.0001

Data Index: 414275 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7981. Min Act: -0.0001

Data Index: 362906 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1057041 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7394. Min Act: -0.0001

Data Index: 327976 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1180504 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6838. Min Act: -0.0001

Data Index: 304648 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7176. Min Act: -0.0001

Data Index: 479730 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7696. Min Act: -0.0001

Data Index: 6386 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6652. Min Act: -0.0001

Data Index: 1254489 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6702. Min Act: -0.0001

Data Index: 590051 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6544. Min Act: -0.0001

Data Index: 820998 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6593. Min Act: -0.0001

Data Index: 153982 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5839. Min Act: -0.0001

Data Index: 1132248 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6384. Min Act: -0.0001

Data Index: 1124653 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6699. Min Act: -0.0001

Data Index: 170912 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6401. Min Act: -0.0001

Data Index: 850947 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6590. Min Act: -0.0001

Data Index: 884489 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1192776 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7186. Min Act: -0.0001

Data Index: 281697 (C4 (Web Text))

Max Activating Token Index: 221