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

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

Neuron 133 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.3482. Min Act: -0.0000

Data Index: 938504 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.3023. Min Act: -0.0000

Data Index: 166708 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.2409. Min Act: -0.0000

Data Index: 907444 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.2209. Min Act: -0.0000

Data Index: 20101 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1213. Min Act: -0.0000

Data Index: 680883 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1158647 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1354574 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0262. Min Act: -0.0000

Data Index: 924559 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0685. Min Act: -0.0000

Data Index: 836735 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0185. Min Act: -0.0000

Data Index: 180665 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1247. Min Act: -0.0000

Data Index: 957409 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0500. Min Act: -0.0000

Data Index: 693539 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1273326 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0426. Min Act: -0.0000

Data Index: 339724 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9478. Min Act: -0.0000

Data Index: 617081 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0052. Min Act: -0.0000

Data Index: 879011 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0537. Min Act: -0.0000

Data Index: 379887 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1272256 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9665. Min Act: -0.0000

Data Index: 154234 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9592. Min Act: -0.0000

Data Index: 565645 (C4 (Web Text))

Max Activating Token Index: 49