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

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

Neuron 1160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.2139. Min Act: -0.0002

Data Index: 640271 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.3216. Min Act: -0.0002

Data Index: 496468 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.2787. Min Act: -0.0002

Data Index: 511911 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1905. Min Act: -0.0001

Data Index: 13125 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.2913. Min Act: -0.0001

Data Index: 986016 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1675. Min Act: -0.0002

Data Index: 491445 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1562. Min Act: -0.0002

Data Index: 1106818 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1041. Min Act: -0.0002

Data Index: 1025175 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.2819. Min Act: -0.0002

Data Index: 294759 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.2290. Min Act: -0.0002

Data Index: 580156 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1596. Min Act: -0.0002

Data Index: 136579 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1520. Min Act: -0.0001

Data Index: 993463 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1793. Min Act: -0.0002

Data Index: 29020 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1811. Min Act: -0.0002

Data Index: 819887 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0409. Min Act: -0.0002

Data Index: 92464 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1409. Min Act: -0.0002

Data Index: 71785 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0947. Min Act: -0.0001

Data Index: 762960 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1942. Min Act: -0.0002

Data Index: 961503 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1877. Min Act: -0.0002

Data Index: 603413 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1850. Min Act: -0.0002

Data Index: 304410 (C4 (Web Text))

Max Activating Token Index: 1016