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

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

Neuron 3738 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.6323. Min Act: -0.0000

Data Index: 6759 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1523956 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1562017 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5302. Min Act: -0.0000

Data Index: 763265 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1556669 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1530753 (Python Code)

Max Activating Token Index: 653

Text #6

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5058. Min Act: -0.0000

Data Index: 640058 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1152934 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5072. Min Act: -0.0000

Data Index: 992509 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1651260 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4539. Min Act: -0.0000

Data Index: 630500 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4938. Min Act: -0.0000

Data Index: 497755 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4720. Min Act: -0.0000

Data Index: 975542 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1103067 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4293. Min Act: -0.0000

Data Index: 603297 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1227450 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4516. Min Act: -0.0000

Data Index: 234702 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4061. Min Act: -0.0000

Data Index: 551437 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4503. Min Act: -0.0000

Data Index: 238963 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4457. Min Act: -0.0000

Data Index: 780651 (C4 (Web Text))

Max Activating Token Index: 137