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

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

Neuron 3522 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1033889 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1238337 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0245. Min Act: -0.0002

Data Index: 366529 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0233. Min Act: -0.0002

Data Index: 185393 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1052140 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0225. Min Act: -0.0002

Data Index: 122820 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0223. Min Act: -0.0001

Data Index: 770366 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1028319 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1259939 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1234892 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0209. Min Act: -0.0001

Data Index: 113959 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0211. Min Act: -0.0001

Data Index: 958239 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0211. Min Act: -0.0002

Data Index: 279490 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0210. Min Act: -0.0002

Data Index: 161351 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1003667 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0203. Min Act: -0.0002

Data Index: 359858 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1044483 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0201. Min Act: -0.0002

Data Index: 143003 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0199. Min Act: -0.0001

Data Index: 545822 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0196. Min Act: -0.0002

Data Index: 660774 (C4 (Web Text))

Max Activating Token Index: 287