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

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

Neuron 72 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: 0.3699. Min Range: -0.3699

Max Act: 0.3699. Min Act: -0.0000

Data Index: 23162 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3539. Min Act: -0.0000

Data Index: 101357 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3449. Min Act: -0.0000

Data Index: 433456 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3504. Min Act: -0.0000

Data Index: 65692 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3530. Min Act: -0.0000

Data Index: 238807 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3160. Min Act: -0.0000

Data Index: 27510 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.3153. Min Act: -0.0000

Data Index: 26070 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2984. Min Act: -0.0000

Data Index: 857839 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2757. Min Act: -0.0000

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2645. Min Act: -0.0000

Data Index: 250709 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1330189 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2510. Min Act: -0.0000

Data Index: 276844 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2476. Min Act: -0.0000

Data Index: 331668 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2791. Min Act: -0.0000

Data Index: 957716 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2636. Min Act: -0.0000

Data Index: 978920 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2565. Min Act: -0.0000

Data Index: 544108 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1047089 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2603. Min Act: -0.0000

Data Index: 506018 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.3699. Min Range: -0.3699

Max Act: 0.2525. Min Act: -0.0000

Data Index: 644701 (C4 (Web Text))

Max Activating Token Index: 381