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

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

Neuron 5285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.3389. Min Act: -0.0000

Data Index: 1053718 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.9017. Min Act: -0.0000

Data Index: 691945 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.9900. Min Act: -0.0000

Data Index: 246871 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6115. Min Act: -0.0000

Data Index: 916735 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.7181. Min Act: -0.0000

Data Index: 465976 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.5477. Min Act: -0.0000

Data Index: 146715 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6653. Min Act: -0.0000

Data Index: 1008996 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6563. Min Act: -0.0000

Data Index: 863506 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6439. Min Act: -0.0000

Data Index: 1102233 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4941. Min Act: -0.0000

Data Index: 850667 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4413. Min Act: -0.0000

Data Index: 1018971 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6817. Min Act: -0.0000

Data Index: 246225 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4241. Min Act: -0.0000

Data Index: 412156 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6695. Min Act: -0.0000

Data Index: 101756 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4110. Min Act: -0.0000

Data Index: 1005825 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.6533. Min Act: -0.0000

Data Index: 454606 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4748. Min Act: -0.0000

Data Index: 942983 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4545. Min Act: -0.0000

Data Index: 278805 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.4374. Min Act: -0.0000

Data Index: 1599499 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 3.3389. Min Range: -3.3389

Max Act: 2.2978. Min Act: -0.0000

Data Index: 1262395 (C4 (Web Text))

Max Activating Token Index: 549