Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3277. Min Range: -3.3277

Max Act: 3.3277. Min Act: -0.0001

Data Index: 1228629 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.9367. Min Act: -0.0001

Data Index: 1356521 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.7210. Min Act: -0.0000

Data Index: 1087897 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.8014. Min Act: -0.0001

Data Index: 912340 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.7266. Min Act: -0.0000

Data Index: 945766 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.6732. Min Act: -0.0001

Data Index: 463026 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.5239. Min Act: -0.0001

Data Index: 1063691 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.5331. Min Act: -0.0000

Data Index: 1236064 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.4744. Min Act: -0.0001

Data Index: 1277332 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.7951. Min Act: -0.0001

Data Index: 1099395 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.3473. Min Act: -0.0001

Data Index: 367232 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.4587. Min Act: -0.0001

Data Index: 1093912 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.3385. Min Act: -0.0000

Data Index: 578823 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.4418. Min Act: -0.0001

Data Index: 338712 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.2713. Min Act: -0.0001

Data Index: 239254 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.3867. Min Act: -0.0001

Data Index: 14458 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.2677. Min Act: -0.0000

Data Index: 845609 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.3633. Min Act: -0.0000

Data Index: 29965 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.3697. Min Act: -0.0000

Data Index: 509704 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.3277. Min Range: -3.3277

Max Act: 2.2107. Min Act: -0.0001

Data Index: 1296632 (C4 (Web Text))

Max Activating Token Index: 422