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

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

Neuron 3680 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.7194. Min Act: -0.0000

Data Index: 64114 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.7710. Min Act: -0.0000

Data Index: 706375 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1111628 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1059651 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6943. Min Act: -0.0000

Data Index: 167967 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6707. Min Act: -0.0000

Data Index: 602445 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6881. Min Act: -0.0000

Data Index: 935097 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6629. Min Act: -0.0000

Data Index: 280041 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.5836. Min Act: -0.0000

Data Index: 975935 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6120. Min Act: -0.0000

Data Index: 639981 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6261. Min Act: -0.0000

Data Index: 638843 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6005. Min Act: -0.0000

Data Index: 306666 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6212. Min Act: -0.0000

Data Index: 319539 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6197. Min Act: -0.0000

Data Index: 842565 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1287477 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1068179 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1041738 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.6196. Min Act: -0.0000

Data Index: 218113 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.7710. Min Range: -0.7710

Max Act: 0.5847. Min Act: -0.0000

Data Index: 328492 (C4 (Web Text))

Max Activating Token Index: 717