Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.7252. Min Act: -0.0000

Data Index: 111439 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1119388 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5891. Min Act: -0.0000

Data Index: 658635 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5662. Min Act: -0.0000

Data Index: 976186 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.6139. Min Act: -0.0000

Data Index: 941448 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1207063 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5879. Min Act: -0.0000

Data Index: 280765 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4893. Min Act: -0.0001

Data Index: 68986 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5154. Min Act: -0.0000

Data Index: 881102 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5084. Min Act: -0.0001

Data Index: 1117871 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5383. Min Act: -0.0000

Data Index: 259314 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4876. Min Act: -0.0001

Data Index: 1336895 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4893. Min Act: -0.0000

Data Index: 941756 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5600. Min Act: -0.0000

Data Index: 443755 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4911. Min Act: -0.0000

Data Index: 190136 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5171. Min Act: -0.0000

Data Index: 546354 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5250. Min Act: -0.0000

Data Index: 39801 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5065. Min Act: -0.0000

Data Index: 352815 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5013. Min Act: -0.0001

Data Index: 554589 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4948. Min Act: -0.0000

Data Index: 862534 (C4 (Web Text))

Max Activating Token Index: 701