Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4144 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0047. Min Range: -1.0047

Max Act: 1.0047. Min Act: -0.0000

Data Index: 33656 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.8097. Min Act: -0.0000

Data Index: 16141 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7280. Min Act: -0.0000

Data Index: 396035 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7636. Min Act: -0.0000

Data Index: 120713 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7128. Min Act: -0.0000

Data Index: 182549 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7296. Min Act: -0.0000

Data Index: 500285 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7236. Min Act: -0.0000

Data Index: 356473 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6573. Min Act: -0.0000

Data Index: 876385 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6578. Min Act: -0.0000

Data Index: 263653 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1123704 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6969. Min Act: -0.0000

Data Index: 410958 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1345733 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.7021. Min Act: -0.0000

Data Index: 170540 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1332182 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6794. Min Act: -0.0000

Data Index: 517806 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6410. Min Act: -0.0000

Data Index: 779822 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6384. Min Act: -0.0000

Data Index: 465766 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6357. Min Act: -0.0000

Data Index: 340709 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1338456 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.0047. Min Range: -1.0047

Max Act: 0.6123. Min Act: -0.0000

Data Index: 124509 (C4 (Web Text))

Max Activating Token Index: 334