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

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

Neuron 2225 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1531. Min Range: -3.1531

Max Act: 3.1531. Min Act: -0.0000

Data Index: 695247 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.5496. Min Act: -0.0000

Data Index: 1453114 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.4247. Min Act: -0.0000

Data Index: 317892 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.1714. Min Act: -0.0000

Data Index: 1090027 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.2720. Min Act: -0.0000

Data Index: 1617629 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.1053. Min Act: -0.0000

Data Index: 613154 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.0869. Min Act: -0.0000

Data Index: 1613652 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.9588. Min Act: -0.0000

Data Index: 270493 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.2011. Min Act: -0.0000

Data Index: 1501730 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.0596. Min Act: -0.0000

Data Index: 234838 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.1363. Min Act: -0.0000

Data Index: 1479045 (Python Code)

Max Activating Token Index: 659

Text #11

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.9326. Min Act: -0.0000

Data Index: 934664 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.0116. Min Act: -0.0000

Data Index: 259106 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.9992. Min Act: -0.0000

Data Index: 1488729 (Python Code)

Max Activating Token Index: 234

Text #14

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.8462. Min Act: -0.0000

Data Index: 946353 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 3.1531. Min Range: -3.1531

Max Act: 2.0379. Min Act: -0.0000

Data Index: 1285446 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.9422. Min Act: -0.0000

Data Index: 1525035 (Python Code)

Max Activating Token Index: 226

Text #17

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.9143. Min Act: -0.0000

Data Index: 1012261 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1339277 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.1531. Min Range: -3.1531

Max Act: 1.8904. Min Act: -0.0000

Data Index: 1058930 (C4 (Web Text))

Max Activating Token Index: 531