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

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

Neuron 1624 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1093003 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1028479 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1090032 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6288. Min Act: -0.0000

Data Index: 853268 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1252630 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5903. Min Act: -0.0000

Data Index: 909020 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6414. Min Act: -0.0000

Data Index: 257327 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5976. Min Act: -0.0001

Data Index: 602113 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5699. Min Act: -0.0001

Data Index: 577820 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5538. Min Act: -0.0000

Data Index: 314307 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1207064 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5858. Min Act: -0.0000

Data Index: 232367 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5417. Min Act: -0.0001

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5537. Min Act: -0.0001

Data Index: 461708 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5604. Min Act: -0.0000

Data Index: 300539 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5207. Min Act: -0.0001

Data Index: 1005710 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1097457 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1312769 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.5048. Min Act: -0.0000

Data Index: 717497 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.6698. Min Range: -0.6698

Max Act: 0.4937. Min Act: -0.0000

Data Index: 598638 (C4 (Web Text))

Max Activating Token Index: 384