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

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

Neuron 4286 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: 0.5674. Min Range: -0.5674

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1239397 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1185443 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.5219. Min Act: -0.0000

Data Index: 968415 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.5088. Min Act: -0.0000

Data Index: 762892 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4775. Min Act: -0.0000

Data Index: 850104 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4759. Min Act: -0.0000

Data Index: 534674 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1231945 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4565. Min Act: -0.0000

Data Index: 31283 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4551. Min Act: 0.0000

Data Index: 103231 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4283. Min Act: -0.0000

Data Index: 837440 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1099956 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1357800 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4190. Min Act: -0.0000

Data Index: 586119 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4176. Min Act: -0.0000

Data Index: 813790 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4155. Min Act: -0.0000

Data Index: 539660 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1269053 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.4019. Min Act: -0.0000

Data Index: 758516 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.3848. Min Act: -0.0000

Data Index: 319678 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.3657. Min Act: -0.0000

Data Index: 678563 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.5674. Min Range: -0.5674

Max Act: 0.3777. Min Act: -0.0000

Data Index: 452190 (C4 (Web Text))

Max Activating Token Index: 709