Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 636 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2740. Min Act: -0.0001

Data Index: 205423 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2689. Min Act: -0.0000

Data Index: 271251 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1063809 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2644. Min Act: -0.0000

Data Index: 172236 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2621. Min Act: -0.0000

Data Index: 790813 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2600. Min Act: -0.0001

Data Index: 158172 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2255. Min Act: -0.0000

Data Index: 12158 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2275. Min Act: -0.0000

Data Index: 409080 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2274. Min Act: -0.0000

Data Index: 525209 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1268441 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2174. Min Act: -0.0000

Data Index: 305984 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2209. Min Act: -0.0000

Data Index: 655599 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2157. Min Act: -0.0000

Data Index: 582871 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2228. Min Act: -0.0000

Data Index: 16797 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2184. Min Act: -0.0001

Data Index: 144760 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2194. Min Act: -0.0000

Data Index: 384147 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2094. Min Act: -0.0000

Data Index: 672054 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2162. Min Act: -0.0001

Data Index: 404332 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2149. Min Act: -0.0000

Data Index: 524063 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2127. Min Act: -0.0001

Data Index: 914093 (C4 (Web Text))

Max Activating Token Index: 678