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

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

Neuron 3026 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: 0.7717. Min Range: -0.7717

Max Act: 0.7717. Min Act: -0.0000

Data Index: 818165 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7489. Min Act: -0.0000

Data Index: 475682 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7022. Min Act: -0.0000

Data Index: 565957 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7234. Min Act: -0.0000

Data Index: 725760 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1080862 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1039243 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6864. Min Act: -0.0000

Data Index: 151379 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6553. Min Act: -0.0000

Data Index: 221304 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6569. Min Act: -0.0000

Data Index: 746497 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6255. Min Act: -0.0000

Data Index: 720913 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6260. Min Act: -0.0000

Data Index: 154316 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6167. Min Act: -0.0000

Data Index: 957915 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5893. Min Act: -0.0000

Data Index: 293670 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5894. Min Act: -0.0000

Data Index: 709958 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6209. Min Act: -0.0000

Data Index: 51984 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6223. Min Act: -0.0000

Data Index: 76399 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6145. Min Act: -0.0000

Data Index: 915812 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5881. Min Act: -0.0000

Data Index: 647265 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5700. Min Act: -0.0000

Data Index: 353072 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5890. Min Act: -0.0000

Data Index: 278845 (C4 (Web Text))

Max Activating Token Index: 736