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

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

Neuron 2344 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1589831 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4691. Min Act: -0.0000

Data Index: 977909 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4321. Min Act: -0.0000

Data Index: 241988 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1552178 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4340. Min Act: -0.0000

Data Index: 58369 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1086293 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1290686 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1551766 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4000. Min Act: -0.0000

Data Index: 295739 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4143. Min Act: -0.0000

Data Index: 841781 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4049. Min Act: -0.0000

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4286. Min Act: -0.0000

Data Index: 313889 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1243483 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4069. Min Act: -0.0000

Data Index: 248443 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3859. Min Act: -0.0000

Data Index: 935413 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1423609 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4088. Min Act: -0.0000

Data Index: 415114 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1033888 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.4219. Min Act: -0.0000

Data Index: 550967 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.4933. Min Range: -0.4933

Max Act: 0.3801. Min Act: -0.0000

Data Index: 795025 (C4 (Web Text))

Max Activating Token Index: 442