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

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

Neuron 2591 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.6048. Min Act: -0.0001

Data Index: 409661 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5464. Min Act: -0.0001

Data Index: 1050938 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1224409 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4815. Min Act: -0.0000

Data Index: 845910 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4788. Min Act: -0.0001

Data Index: 14689 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.5001. Min Act: -0.0000

Data Index: 577463 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4343. Min Act: -0.0000

Data Index: 427938 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1039330 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4154. Min Act: -0.0001

Data Index: 1357741 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4156. Min Act: -0.0001

Data Index: 1200882 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4026. Min Act: -0.0001

Data Index: 764273 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1186721 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3836. Min Act: -0.0001

Data Index: 891171 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1052284 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1285695 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3721. Min Act: -0.0000

Data Index: 58970 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1067032 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3930. Min Act: -0.0001

Data Index: 351698 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3756. Min Act: -0.0001

Data Index: 439244 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.6048. Min Range: -0.6048

Max Act: 0.3751. Min Act: -0.0001

Data Index: 198059 (C4 (Web Text))

Max Activating Token Index: 816