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

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

Neuron 2324 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.9982. Min Act: -0.0001

Data Index: 1093871 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6893. Min Act: -0.0001

Data Index: 428968 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6810. Min Act: -0.0001

Data Index: 226423 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6735. Min Act: -0.0001

Data Index: 1244432 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.7464. Min Act: -0.0001

Data Index: 917702 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6591. Min Act: -0.0001

Data Index: 975268 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6857. Min Act: -0.0001

Data Index: 428885 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.5196. Min Act: -0.0001

Data Index: 1086624 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.4651. Min Act: -0.0001

Data Index: 1257525 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.4676. Min Act: -0.0001

Data Index: 1355423 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.4381. Min Act: -0.0001

Data Index: 1169042 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3204. Min Act: -0.0001

Data Index: 592326 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.5253. Min Act: -0.0001

Data Index: 372630 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3025. Min Act: -0.0001

Data Index: 1222138 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.2735. Min Act: -0.0001

Data Index: 84921 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3621. Min Act: -0.0001

Data Index: 482690 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3887. Min Act: -0.0001

Data Index: 240933 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3873. Min Act: -0.0001

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3408. Min Act: -0.0001

Data Index: 865766 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3690. Min Act: -0.0001

Data Index: 765775 (C4 (Web Text))

Max Activating Token Index: 768