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

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

Neuron 3750 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.6016. Min Act: -0.0000

Data Index: 799105 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1302312 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5184. Min Act: -0.0000

Data Index: 388403 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1324999 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5148. Min Act: -0.0000

Data Index: 397062 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5044. Min Act: -0.0000

Data Index: 733101 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5199. Min Act: -0.0000

Data Index: 319974 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1110046 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4794. Min Act: -0.0000

Data Index: 392254 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4882. Min Act: -0.0000

Data Index: 224952 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4694. Min Act: -0.0000

Data Index: 976779 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1012274 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4873. Min Act: -0.0000

Data Index: 922414 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1234897 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.5234. Min Act: -0.0000

Data Index: 70327 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4545. Min Act: -0.0000

Data Index: 100413 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4703. Min Act: -0.0000

Data Index: 839451 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.3758. Min Act: -0.0000

Data Index: 131304 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4629. Min Act: -0.0000

Data Index: 814151 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.6016. Min Range: -0.6016

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1408967 (Python Code)

Max Activating Token Index: 531