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

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

Neuron 2388 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: 0.8263. Min Range: -0.8263

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1014682 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7261. Min Act: -0.0001

Data Index: 309848 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1212062 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7153. Min Act: -0.0001

Data Index: 781564 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7046. Min Act: -0.0000

Data Index: 880451 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6523. Min Act: -0.0001

Data Index: 1325034 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6173. Min Act: -0.0000

Data Index: 281810 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6086. Min Act: -0.0000

Data Index: 325337 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6249. Min Act: -0.0000

Data Index: 371141 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6247. Min Act: -0.0000

Data Index: 370988 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6340. Min Act: 0.0001

Data Index: 843411 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1077753 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6059. Min Act: -0.0000

Data Index: 17192 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1285097 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5888. Min Act: 0.0001

Data Index: 713362 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5684. Min Act: -0.0000

Data Index: 154269 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1167498 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5859. Min Act: -0.0001

Data Index: 933743 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5744. Min Act: -0.0001

Data Index: 922911 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1041685 (C4 (Web Text))

Max Activating Token Index: 902