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

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

Neuron 691 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: 1.9068. Min Range: -1.9068

Max Act: 1.9068. Min Act: -0.0000

Data Index: 101515 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.7018. Min Act: -0.0000

Data Index: 945702 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.5838. Min Act: -0.0000

Data Index: 110084 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1028851 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.5327. Min Act: -0.0000

Data Index: 1053345 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.7044. Min Act: -0.0000

Data Index: 929082 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.6173. Min Act: -0.0000

Data Index: 501004 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.5410. Min Act: -0.0000

Data Index: 954510 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.6070. Min Act: -0.0000

Data Index: 171287 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.6108. Min Act: -0.0000

Data Index: 621841 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1237171 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1306176 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1352345 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.6289. Min Act: -0.0000

Data Index: 396267 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.5226. Min Act: -0.0000

Data Index: 592518 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.4894. Min Act: -0.0000

Data Index: 591082 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.4851. Min Act: -0.0000

Data Index: 581506 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.5501. Min Act: -0.0000

Data Index: 618890 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.4468. Min Act: -0.0000

Data Index: 807961 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.4389. Min Act: -0.0000

Data Index: 429113 (C4 (Web Text))

Max Activating Token Index: 641