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

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

Neuron 1919 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.8977. Min Act: -0.0001

Data Index: 2802 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7485. Min Act: -0.0001

Data Index: 821630 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1442674 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.6772. Min Act: -0.0001

Data Index: 872664 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.7288. Min Act: -0.0001

Data Index: 714311 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.5913. Min Act: -0.0001

Data Index: 544875 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1580716 (Python Code)

Max Activating Token Index: 578

Text #7

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1385300 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4924. Min Act: -0.0001

Data Index: 58078 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4780. Min Act: -0.0000

Data Index: 1595285 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1637388 (Python Code)

Max Activating Token Index: 279

Text #11

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.4545. Min Act: -0.0001

Data Index: 1616336 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1391748 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1349613 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3760. Min Act: -0.0001

Data Index: 671022 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1374970 (Python Code)

Max Activating Token Index: 304

Text #16

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1482973 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.2372. Min Act: -0.0001

Data Index: 59193 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.1020. Min Act: -0.0001

Data Index: 1460368 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 1.8977. Min Range: -1.8977

Max Act: 1.3110. Min Act: -0.0000

Data Index: 778814 (C4 (Web Text))

Max Activating Token Index: 691