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

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

Neuron 3266 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: 0.3500. Min Range: -0.3500

Max Act: 0.3500. Min Act: -0.0000

Data Index: 630249 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.3130. Min Act: -0.0000

Data Index: 390169 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2678. Min Act: -0.0000

Data Index: 332388 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2724. Min Act: -0.0000

Data Index: 922638 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1428652 (Python Code)

Max Activating Token Index: 957

Text #5

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2563. Min Act: -0.0000

Data Index: 669008 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2524. Min Act: -0.0001

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2603. Min Act: -0.0000

Data Index: 680963 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1236887 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2413. Min Act: -0.0000

Data Index: 511997 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2170. Min Act: -0.0000

Data Index: 191596 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1295140 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2196. Min Act: -0.0000

Data Index: 544092 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2197. Min Act: -0.0000

Data Index: 516062 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2246. Min Act: -0.0000

Data Index: 956781 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1260097 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2190. Min Act: -0.0000

Data Index: 241992 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2196. Min Act: -0.0000

Data Index: 351360 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.3500. Min Range: -0.3500

Max Act: 0.2167. Min Act: -0.0000

Data Index: 185006 (C4 (Web Text))

Max Activating Token Index: 687