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

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

Neuron 5432 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 20.2679. Min Range: -20.2679

Max Act: 20.2679. Min Act: -0.0000

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 20.2679. Min Range: -20.2679

Max Act: 19.1282. Min Act: -0.0000

Data Index: 1346105 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.6106. Min Act: -0.0000

Data Index: 492923 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 20.2679. Min Range: -20.2679

Max Act: 18.6261. Min Act: 0.0002

Data Index: 1210662 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 20.2679. Min Range: -20.2679

Max Act: 18.2444. Min Act: -0.0000

Data Index: 171700 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 20.2679. Min Range: -20.2679

Max Act: 15.4043. Min Act: -0.0000

Data Index: 1423420 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 20.2679. Min Range: -20.2679

Max Act: 16.7198. Min Act: -0.0000

Data Index: 1275216 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.9876. Min Act: -0.0000

Data Index: 621018 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.6050. Min Act: -0.0000

Data Index: 351366 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.8589. Min Act: -0.0000

Data Index: 1147575 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.9838. Min Act: -0.0000

Data Index: 367054 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.3550. Min Act: -0.0000

Data Index: 16392 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 20.2679. Min Range: -20.2679

Max Act: 16.8046. Min Act: -0.0000

Data Index: 456304 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.9877. Min Act: -0.0000

Data Index: 1307888 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 20.2679. Min Range: -20.2679

Max Act: 16.4826. Min Act: -0.0000

Data Index: 1212451 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 20.2679. Min Range: -20.2679

Max Act: 16.5004. Min Act: -0.0000

Data Index: 1008946 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 20.2679. Min Range: -20.2679

Max Act: 16.5732. Min Act: -0.0000

Data Index: 1125420 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 20.2679. Min Range: -20.2679

Max Act: 16.0236. Min Act: -0.0000

Data Index: 605372 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 20.2679. Min Range: -20.2679

Max Act: 17.0723. Min Act: -0.0000

Data Index: 729140 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 20.2679. Min Range: -20.2679

Max Act: 15.3514. Min Act: -0.0000

Data Index: 529605 (C4 (Web Text))

Max Activating Token Index: 567