Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3632. Min Act: -0.0001

Data Index: 459096 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3255. Min Act: -0.0001

Data Index: 472668 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3237. Min Act: -0.0000

Data Index: 303427 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3088. Min Act: -0.0000

Data Index: 549519 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2976. Min Act: -0.0000

Data Index: 388812 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1244780 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2929. Min Act: -0.0001

Data Index: 140898 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1166344 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1275849 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2849. Min Act: -0.0000

Data Index: 806008 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2706. Min Act: -0.0000

Data Index: 234166 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2764. Min Act: -0.0001

Data Index: 1162415 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2666. Min Act: -0.0000

Data Index: 388361 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2757. Min Act: -0.0000

Data Index: 122735 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1056114 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2794. Min Act: -0.0000

Data Index: 80747 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2521. Min Act: -0.0001

Data Index: 268791 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2536. Min Act: -0.0000

Data Index: 275406 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1029379 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2663. Min Act: -0.0000

Data Index: 52150 (C4 (Web Text))

Max Activating Token Index: 93