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

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

Neuron 4750 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: 1.5226. Min Range: -1.5226

Max Act: 1.5226. Min Act: -0.0001

Data Index: 655886 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.4761. Min Act: -0.0001

Data Index: 1021578 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3631. Min Act: -0.0000

Data Index: 838383 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3054. Min Act: -0.0000

Data Index: 155415 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1347313 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3246. Min Act: -0.0000

Data Index: 357336 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1094879 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3857. Min Act: -0.0001

Data Index: 844177 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.4655. Min Act: -0.0001

Data Index: 898732 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3597. Min Act: -0.0001

Data Index: 1331730 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1001636 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2814. Min Act: -0.0000

Data Index: 399171 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2560. Min Act: -0.0001

Data Index: 820382 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2916. Min Act: -0.0000

Data Index: 920131 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2353. Min Act: -0.0001

Data Index: 1213903 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.3246. Min Act: -0.0001

Data Index: 451302 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.1244. Min Act: -0.0000

Data Index: 406311 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2303. Min Act: -0.0000

Data Index: 318772 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2241. Min Act: -0.0000

Data Index: 204969 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.5226. Min Range: -1.5226

Max Act: 1.2816. Min Act: -0.0001

Data Index: 622591 (C4 (Web Text))

Max Activating Token Index: 108