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

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

Neuron 3850 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: 3.3281. Min Range: -3.3281

Max Act: 3.3281. Min Act: -0.0000

Data Index: 139995 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 3.3281. Min Range: -3.3281

Max Act: 3.0843. Min Act: -0.0000

Data Index: 616120 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.8461. Min Act: -0.0000

Data Index: 48133 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.8919. Min Act: -0.0000

Data Index: 482014 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.7163. Min Act: -0.0000

Data Index: 1162941 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.8232. Min Act: -0.0000

Data Index: 1352142 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.7640. Min Act: -0.0000

Data Index: 1274132 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.6404. Min Act: -0.0000

Data Index: 851169 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3257. Min Act: -0.0000

Data Index: 1326849 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.2987. Min Act: -0.0000

Data Index: 558916 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.5117. Min Act: -0.0000

Data Index: 420195 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3161. Min Act: -0.0000

Data Index: 457651 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.4029. Min Act: -0.0000

Data Index: 270067 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3942. Min Act: -0.0000

Data Index: 1281797 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1207817 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3822. Min Act: -0.0000

Data Index: 224139 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1353218 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3496. Min Act: -0.0000

Data Index: 1273198 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.2085. Min Act: -0.0000

Data Index: 462097 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 3.3281. Min Range: -3.3281

Max Act: 2.3276. Min Act: -0.0000

Data Index: 543182 (C4 (Web Text))

Max Activating Token Index: 986