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

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

Neuron 4564 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: 3.5249. Min Range: -3.5249

Max Act: 3.5249. Min Act: -0.0000

Data Index: 995171 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 3.5249. Min Range: -3.5249

Max Act: 2.3062. Min Act: -0.0000

Data Index: 1111983 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.5249. Min Range: -3.5249

Max Act: 2.2792. Min Act: -0.0000

Data Index: 276438 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 3.5249. Min Range: -3.5249

Max Act: 2.4557. Min Act: -0.0000

Data Index: 1319413 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 3.5249. Min Range: -3.5249

Max Act: 2.1415. Min Act: -0.0000

Data Index: 1076898 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 3.5249. Min Range: -3.5249

Max Act: 2.2242. Min Act: -0.0000

Data Index: 726423 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.9887. Min Act: -0.0000

Data Index: 16982 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.9849. Min Act: -0.0000

Data Index: 588948 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.8920. Min Act: -0.0000

Data Index: 421940 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 3.5249. Min Range: -3.5249

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1074425 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1117230 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1152878 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.8020. Min Act: -0.0000

Data Index: 338493 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.6984. Min Act: -0.0000

Data Index: 422880 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.7422. Min Act: -0.0000

Data Index: 761021 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.6636. Min Act: -0.0000

Data Index: 637049 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.5948. Min Act: -0.0000

Data Index: 265738 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1135189 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.5548. Min Act: -0.0000

Data Index: 538863 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 3.5249. Min Range: -3.5249

Max Act: 1.4110. Min Act: -0.0000

Data Index: 805181 (C4 (Web Text))

Max Activating Token Index: 542