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

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

Neuron 4577 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.9097. Min Act: -0.0000

Data Index: 271223 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.8919. Min Act: -0.0000

Data Index: 657007 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.9092. Min Act: -0.0000

Data Index: 456505 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.9626. Min Act: -0.0000

Data Index: 716733 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1035461 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1224089 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7813. Min Act: -0.0000

Data Index: 371741 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.8121. Min Act: -0.0000

Data Index: 595626 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.8320. Min Act: -0.0000

Data Index: 871098 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.8140. Min Act: -0.0000

Data Index: 568243 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7663. Min Act: -0.0000

Data Index: 411344 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7997. Min Act: -0.0000

Data Index: 785934 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1090326 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7387. Min Act: -0.0000

Data Index: 723317 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7007. Min Act: -0.0000

Data Index: 520975 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.6968. Min Act: -0.0000

Data Index: 174038 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.7213. Min Act: -0.0000

Data Index: 129474 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.6639. Min Act: -0.0000

Data Index: 908677 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.6870. Min Act: -0.0000

Data Index: 12751 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.6917. Min Act: -0.0000

Data Index: 507791 (C4 (Web Text))

Max Activating Token Index: 436