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

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

Neuron 3251 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: 0.6813. Min Range: -0.6813

Max Act: 0.6813. Min Act: -0.0000

Data Index: 825570 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6436. Min Act: -0.0000

Data Index: 74669 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1124163 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6300. Min Act: -0.0000

Data Index: 474846 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5774. Min Act: -0.0000

Data Index: 580028 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5767. Min Act: -0.0000

Data Index: 401682 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5441. Min Act: -0.0000

Data Index: 778443 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1237325 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5087. Min Act: -0.0000

Data Index: 454609 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5212. Min Act: -0.0000

Data Index: 751382 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1213604 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4623. Min Act: -0.0000

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1005173 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1276609 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1236701 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4905. Min Act: -0.0000

Data Index: 31068 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4641. Min Act: -0.0000

Data Index: 286701 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4634. Min Act: -0.0000

Data Index: 387369 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4762. Min Act: -0.0000

Data Index: 501693 (C4 (Web Text))

Max Activating Token Index: 379