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

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

Neuron 4843 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.7822. Min Act: -0.0000

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.7486. Min Act: -0.0000

Data Index: 1569554 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.6979. Min Act: -0.0000

Data Index: 1408090 (Python Code)

Max Activating Token Index: 1010

Text #3

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.3974. Min Act: -0.0000

Data Index: 1606154 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.5318. Min Act: -0.0000

Data Index: 1025354 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.7605. Min Act: -0.0000

Data Index: 1651822 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.2001. Min Act: -0.0000

Data Index: 641707 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.1076. Min Act: -0.0000

Data Index: 807407 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.9344. Min Act: -0.0000

Data Index: 1208834 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 4.7822. Min Range: -4.7822

Max Act: 4.0908. Min Act: -0.0000

Data Index: 1212915 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.8781. Min Act: -0.0000

Data Index: 576977 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.6198. Min Act: -0.0000

Data Index: 836788 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.6983. Min Act: -0.0000

Data Index: 1315401 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.6708. Min Act: -0.0000

Data Index: 86220 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.7972. Min Act: -0.0000

Data Index: 430480 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.4454. Min Act: -0.0000

Data Index: 1586411 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.7810. Min Act: -0.0000

Data Index: 294992 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.6040. Min Act: -0.0000

Data Index: 1301824 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.5799. Min Act: -0.0000

Data Index: 1094846 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 4.7822. Min Range: -4.7822

Max Act: 3.4064. Min Act: -0.0000

Data Index: 857144 (C4 (Web Text))

Max Activating Token Index: 864