Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1028375 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1086158 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0365. Min Act: -0.0001

Data Index: 49744 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0387. Min Act: -0.0002

Data Index: 121884 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0339. Min Act: -0.0001

Data Index: 809466 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1306072 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0321. Min Act: -0.0001

Data Index: 997503 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0344. Min Act: -0.0002

Data Index: 872479 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0391. Min Act: -0.0001

Data Index: 700624 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0324. Min Act: -0.0001

Data Index: 237453 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1239217 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0311. Min Act: -0.0001

Data Index: 525314 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1261417 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1022631 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0288. Min Act: -0.0002

Data Index: 553864 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0281. Min Act: -0.0002

Data Index: 727148 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0305. Min Act: -0.0001

Data Index: 418385 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1160244 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0307. Min Act: -0.0001

Data Index: 724981 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0318. Min Act: -0.0001

Data Index: 295527 (C4 (Web Text))

Max Activating Token Index: 829