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

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

Neuron 3596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0151. Min Range: -2.0151

Max Act: 2.0077. Min Act: -0.0000

Data Index: 644612 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 2.0151. Min Range: -2.0151

Max Act: 2.0151. Min Act: -0.0000

Data Index: 1296183 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.6452. Min Act: -0.0000

Data Index: 429170 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.7655. Min Act: -0.0000

Data Index: 391533 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.5433. Min Act: -0.0000

Data Index: 124741 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.4736. Min Act: -0.0000

Data Index: 522110 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1198787 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.4253. Min Act: -0.0000

Data Index: 219201 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.4797. Min Act: -0.0000

Data Index: 955453 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.4453. Min Act: -0.0000

Data Index: 370318 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1305717 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.2409. Min Act: -0.0000

Data Index: 612109 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.3834. Min Act: -0.0000

Data Index: 527629 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1076559 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.2711. Min Act: -0.0000

Data Index: 535787 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1133954 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.3066. Min Act: -0.0000

Data Index: 172527 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.2363. Min Act: -0.0000

Data Index: 304755 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.2742. Min Act: -0.0000

Data Index: 334343 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.0151. Min Range: -2.0151

Max Act: 1.1205. Min Act: -0.0000

Data Index: 917531 (C4 (Web Text))

Max Activating Token Index: 233