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

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

Neuron 1630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6488. Min Act: -0.0000

Data Index: 529898 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1122115 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6074. Min Act: -0.0000

Data Index: 341773 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6100. Min Act: -0.0000

Data Index: 835482 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5638. Min Act: -0.0000

Data Index: 554991 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6150. Min Act: -0.0000

Data Index: 777047 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.6279. Min Act: -0.0000

Data Index: 230939 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5954. Min Act: -0.0000

Data Index: 69433 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5919. Min Act: -0.0000

Data Index: 158847 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1176888 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1267478 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1117562 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4938. Min Act: -0.0000

Data Index: 11277 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4959. Min Act: -0.0000

Data Index: 740602 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4802. Min Act: -0.0000

Data Index: 934831 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5291. Min Act: -0.0000

Data Index: 329852 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5009. Min Act: -0.0000

Data Index: 91737 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.5112. Min Act: -0.0000

Data Index: 308557 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1084288 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.6600. Min Range: -0.6600

Max Act: 0.4863. Min Act: -0.0000

Data Index: 797986 (C4 (Web Text))

Max Activating Token Index: 391