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

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

Neuron 3368 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.6446. Min Act: -0.0000

Data Index: 982674 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.6412. Min Act: -0.0000

Data Index: 654887 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.6331. Min Act: 0.0000

Data Index: 43138 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1277229 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5769. Min Act: -0.0000

Data Index: 113015 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1080990 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1049556 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5687. Min Act: -0.0000

Data Index: 666071 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1254192 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5464. Min Act: -0.0000

Data Index: 719287 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5614. Min Act: -0.0000

Data Index: 870636 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1265521 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5638. Min Act: -0.0000

Data Index: 250617 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1357623 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5765. Min Act: -0.0000

Data Index: 484092 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1190845 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5182. Min Act: -0.0000

Data Index: 246665 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4990. Min Act: -0.0000

Data Index: 96158 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1101077 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1019703 (C4 (Web Text))

Max Activating Token Index: 831