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

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

Neuron 3671 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.4181. Min Act: -0.0001

Data Index: 337968 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3975. Min Act: -0.0001

Data Index: 898826 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3620. Min Act: -0.0001

Data Index: 990766 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3600. Min Act: -0.0001

Data Index: 157161 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3349. Min Act: -0.0001

Data Index: 401258 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1243890 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3418. Min Act: -0.0001

Data Index: 492554 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3360. Min Act: -0.0001

Data Index: 748042 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3587. Min Act: -0.0001

Data Index: 686477 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3702. Min Act: -0.0001

Data Index: 43863 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3343. Min Act: -0.0001

Data Index: 351139 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3428. Min Act: -0.0001

Data Index: 965154 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3393. Min Act: -0.0001

Data Index: 266501 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1206414 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3071. Min Act: -0.0001

Data Index: 553176 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3264. Min Act: -0.0001

Data Index: 316754 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3468. Min Act: -0.0001

Data Index: 138617 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1014674 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3247. Min Act: -0.0001

Data Index: 574355 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.4181. Min Range: -0.4181

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1082426 (C4 (Web Text))

Max Activating Token Index: 15