Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1822 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0002

Data Index: 815371 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1327482 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0546. Min Act: -0.0002

Data Index: 198950 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0542. Min Act: -0.0002

Data Index: 454714 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1294938 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0538. Min Act: -0.0002

Data Index: 723909 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0523. Min Act: -0.0001

Data Index: 297277 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0509. Min Act: -0.0002

Data Index: 782412 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1550510 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0496. Min Act: -0.0002

Data Index: 569114 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0489. Min Act: -0.0002

Data Index: 897597 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0497. Min Act: -0.0002

Data Index: 568813 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0490. Min Act: -0.0002

Data Index: 438268 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0470. Min Act: -0.0002

Data Index: 165712 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0485. Min Act: -0.0002

Data Index: 708805 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0479. Min Act: -0.0002

Data Index: 679340 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0478. Min Act: -0.0002

Data Index: 290856 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0475. Min Act: -0.0002

Data Index: 819087 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1588980 (Python Code)

Max Activating Token Index: 409