Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4333 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3256. Min Range: -3.3256

Max Act: 3.3256. Min Act: -0.0000

Data Index: 818352 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.5412. Min Act: -0.0000

Data Index: 1256378 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.5126. Min Act: -0.0000

Data Index: 489780 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.9205. Min Act: -0.0001

Data Index: 588180 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.3214. Min Act: -0.0000

Data Index: 603796 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.5993. Min Act: -0.0000

Data Index: 861053 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.8263. Min Act: -0.0001

Data Index: 1210395 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.5689. Min Act: -0.0001

Data Index: 376300 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.4507. Min Act: -0.0001

Data Index: 985465 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.5574. Min Act: -0.0000

Data Index: 259723 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.4329. Min Act: -0.0001

Data Index: 90659 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.3791. Min Act: -0.0000

Data Index: 241501 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.6224. Min Act: -0.0000

Data Index: 1039822 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.5986. Min Act: -0.0001

Data Index: 660570 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.6224. Min Act: -0.0001

Data Index: 89675 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.3256. Min Range: -3.3256

Max Act: 1.9580. Min Act: -0.0001

Data Index: 270900 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.3054. Min Act: -0.0000

Data Index: 153540 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.2980. Min Act: -0.0001

Data Index: 313993 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.0791. Min Act: -0.0001

Data Index: 1088656 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 3.3256. Min Range: -3.3256

Max Act: 2.0422. Min Act: -0.0000

Data Index: 85513 (C4 (Web Text))

Max Activating Token Index: 121