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

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

Neuron 3649 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6888. Min Act: -0.0000

Data Index: 591349 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.6264. Min Act: -0.0000

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4984. Min Act: -0.0000

Data Index: 477202 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4922. Min Act: -0.0000

Data Index: 930083 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4902. Min Act: -0.0000

Data Index: 274466 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1586910 (Python Code)

Max Activating Token Index: 808

Text #6

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4737. Min Act: -0.0000

Data Index: 960714 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1638699 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1394961 (Python Code)

Max Activating Token Index: 976

Text #9

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1549938 (Python Code)

Max Activating Token Index: 960

Text #10

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5334. Min Act: -0.0000

Data Index: 236018 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1591699 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1515528 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1447955 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1569948 (Python Code)

Max Activating Token Index: 978

Text #15

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4678. Min Act: -0.0000

Data Index: 452168 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1587103 (Python Code)

Max Activating Token Index: 874

Text #17

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1423908 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.5121. Min Act: -0.0000

Data Index: 948985 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.6888. Min Range: -0.6888

Max Act: 0.4897. Min Act: -0.0000

Data Index: 318120 (C4 (Web Text))

Max Activating Token Index: 644