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

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

Neuron 2399 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.6123. Min Act: -0.0001

Data Index: 1516036 (Python Code)

Max Activating Token Index: 740

Text #1

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1585176 (Python Code)

Max Activating Token Index: 442

Text #2

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1483988 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1567139 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1456969 (Python Code)

Max Activating Token Index: 982

Text #5

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.3777. Min Act: -0.0001

Data Index: 1517625 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.2209. Min Act: -0.0000

Data Index: 534037 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1393974 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.1235. Min Act: -0.0001

Data Index: 1484637 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1447104 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.1826. Min Act: -0.0000

Data Index: 53152 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1063311 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1566376 (Python Code)

Max Activating Token Index: 666

Text #13

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1399909 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 1.6123. Min Range: -1.6123

Max Act: 0.9697. Min Act: -0.0001

Data Index: 1366447 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 1.6123. Min Range: -1.6123

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1636458 (Python Code)

Max Activating Token Index: 147

Text #17

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1551716 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1535868 (Python Code)

Max Activating Token Index: 892

Text #19

Max Range: 1.6123. Min Range: -1.6123

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1477937 (Python Code)

Max Activating Token Index: 993