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

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

Neuron 2651 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.6151. Min Act: -0.0000

Data Index: 12564 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.6095. Min Act: -0.0000

Data Index: 663986 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.6021. Min Act: -0.0000

Data Index: 872398 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1201415 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5260. Min Act: 0.0000

Data Index: 488565 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5572. Min Act: 0.0000

Data Index: 335783 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4722. Min Act: 0.0000

Data Index: 629866 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4493. Min Act: -0.0000

Data Index: 269997 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4625. Min Act: -0.0000

Data Index: 114123 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4527. Min Act: 0.0000

Data Index: 411661 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4531. Min Act: -0.0000

Data Index: 165412 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4221. Min Act: -0.0000

Data Index: 849129 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1166117 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4228. Min Act: -0.0000

Data Index: 165906 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4366. Min Act: -0.0000

Data Index: 487384 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4355. Min Act: -0.0000

Data Index: 400607 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4461. Min Act: -0.0000

Data Index: 904813 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4181. Min Act: -0.0000

Data Index: 207678 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4357. Min Act: 0.0000

Data Index: 1002954 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1051301 (C4 (Web Text))

Max Activating Token Index: 751