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

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

Neuron 3072 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: 1.7479. Min Range: -1.7479

Max Act: 1.7479. Min Act: -0.0000

Data Index: 148903 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.7479. Min Range: -1.7479

Max Act: 1.2978. Min Act: -0.0000

Data Index: 207188 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.7479. Min Range: -1.7479

Max Act: 1.1590. Min Act: -0.0000

Data Index: 741646 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 1.7479. Min Range: -1.7479

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1169884 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 1.7479. Min Range: -1.7479

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1282936 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.8071. Min Act: -0.0000

Data Index: 995597 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9435. Min Act: -0.0000

Data Index: 414029 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1175214 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1050921 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.8742. Min Act: -0.0000

Data Index: 133916 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9875. Min Act: -0.0000

Data Index: 503629 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9314. Min Act: -0.0000

Data Index: 824632 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9107. Min Act: -0.0000

Data Index: 899464 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9689. Min Act: -0.0000

Data Index: 64202 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.7492. Min Act: -0.0000

Data Index: 292292 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.8798. Min Act: -0.0000

Data Index: 778989 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.9095. Min Act: -0.0000

Data Index: 551249 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1024693 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.8046. Min Act: -0.0000

Data Index: 485317 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.7479. Min Range: -1.7479

Max Act: 0.8358. Min Act: -0.0000

Data Index: 615606 (C4 (Web Text))

Max Activating Token Index: 340