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

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

Neuron 3201 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: 1.3572. Min Range: -1.3572

Max Act: 1.3572. Min Act: -0.0000

Data Index: 411496 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.2898. Min Act: -0.0000

Data Index: 346278 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.2147. Min Act: -0.0001

Data Index: 491284 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.2079. Min Act: -0.0001

Data Index: 520315 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1014977 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.2368. Min Act: -0.0001

Data Index: 320507 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.1723. Min Act: -0.0000

Data Index: 63024 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.1560. Min Act: -0.0001

Data Index: 1101425 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1184802 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.1022. Min Act: -0.0000

Data Index: 904919 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9959. Min Act: -0.0000

Data Index: 129254 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9708. Min Act: -0.0000

Data Index: 707136 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1103809 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9830. Min Act: -0.0000

Data Index: 489285 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.3572. Min Range: -1.3572

Max Act: 1.0000. Min Act: -0.0000

Data Index: 614553 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9144. Min Act: -0.0000

Data Index: 820891 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9376. Min Act: -0.0000

Data Index: 446867 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9586. Min Act: -0.0001

Data Index: 143844 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.8923. Min Act: -0.0001

Data Index: 646425 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 1.3572. Min Range: -1.3572

Max Act: 0.9171. Min Act: -0.0001

Data Index: 904017 (C4 (Web Text))

Max Activating Token Index: 991