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

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

Neuron 3778 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.5688. Min Act: -0.0000

Data Index: 1308591 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2941. Min Act: -0.0000

Data Index: 909284 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2453. Min Act: -0.0000

Data Index: 540485 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.2130. Min Act: -0.0000

Data Index: 412920 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1179. Min Act: -0.0000

Data Index: 724763 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1701. Min Act: -0.0000

Data Index: 159067 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1285133 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1245. Min Act: -0.0000

Data Index: 145375 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0945. Min Act: -0.0000

Data Index: 304746 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9673. Min Act: -0.0000

Data Index: 682000 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1235032 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9715. Min Act: -0.0000

Data Index: 633892 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0040. Min Act: -0.0000

Data Index: 887715 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.5688. Min Range: -1.5688

Max Act: 1.0036. Min Act: -0.0000

Data Index: 55918 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1031945 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9815. Min Act: -0.0000

Data Index: 269785 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1154963 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9728. Min Act: -0.0000

Data Index: 367340 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.5688. Min Range: -1.5688

Max Act: 0.9622. Min Act: -0.0000

Data Index: 832596 (C4 (Web Text))

Max Activating Token Index: 700