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

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

Neuron 404 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1329911 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6522. Min Act: -0.0000

Data Index: 398303 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1062431 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6028. Min Act: -0.0000

Data Index: 894115 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1142581 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6269. Min Act: -0.0000

Data Index: 819007 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1502673 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1292248 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5641. Min Act: -0.0000

Data Index: 219277 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6005. Min Act: -0.0000

Data Index: 654598 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1216901 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5470. Min Act: -0.0000

Data Index: 71790 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5076. Min Act: -0.0000

Data Index: 797580 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1016710 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5357. Min Act: -0.0000

Data Index: 235931 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1308013 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5613. Min Act: -0.0000

Data Index: 768186 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5329. Min Act: -0.0000

Data Index: 339227 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1504952 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1115274 (C4 (Web Text))

Max Activating Token Index: 672