Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 58 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2072. Min Range: -4.2072

Max Act: 4.2072. Min Act: -0.0000

Data Index: 620220 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 4.2072. Min Range: -4.2072

Max Act: 4.2072. Min Act: -0.0000

Data Index: 777939 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.6595. Min Act: -0.0000

Data Index: 483827 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.5377. Min Act: -0.0000

Data Index: 974256 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.4902. Min Act: -0.0000

Data Index: 516780 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.3899. Min Act: -0.0000

Data Index: 714573 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.3346. Min Act: -0.0000

Data Index: 432186 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.4636. Min Act: -0.0000

Data Index: 189886 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.4391. Min Act: -0.0000

Data Index: 1297017 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.2858. Min Act: -0.0000

Data Index: 1030051 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.3406. Min Act: -0.0000

Data Index: 648825 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.2839. Min Act: -0.0000

Data Index: 7987 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.1855. Min Act: -0.0000

Data Index: 166415 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.3624. Min Act: -0.0000

Data Index: 580678 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 4.2072. Min Range: -4.2072

Max Act: 2.9911. Min Act: -0.0000

Data Index: 435754 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.1400. Min Act: -0.0000

Data Index: 1153844 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.1074. Min Act: -0.0000

Data Index: 1072546 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 4.2072. Min Range: -4.2072

Max Act: 3.0566. Min Act: -0.0000

Data Index: 55540 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 4.2072. Min Range: -4.2072

Max Act: 2.9107. Min Act: -0.0000

Data Index: 1426132 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 4.2072. Min Range: -4.2072

Max Act: 2.9217. Min Act: -0.0000

Data Index: 223816 (C4 (Web Text))

Max Activating Token Index: 743