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

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

Neuron 5861 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: 0.6689. Min Range: -0.6689

Max Act: 0.6689. Min Act: -0.0000

Data Index: 255686 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1148876 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4806. Min Act: -0.0000

Data Index: 725226 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4369. Min Act: -0.0000

Data Index: 210021 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3971. Min Act: -0.0000

Data Index: 880545 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4033. Min Act: -0.0000

Data Index: 485102 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4093. Min Act: -0.0000

Data Index: 27452 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3845. Min Act: -0.0000

Data Index: 801071 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1191267 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3824. Min Act: -0.0000

Data Index: 948817 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3644. Min Act: -0.0000

Data Index: 76630 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3684. Min Act: -0.0000

Data Index: 587377 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3670. Min Act: -0.0000

Data Index: 174254 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3527. Min Act: -0.0000

Data Index: 506573 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1350258 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3704. Min Act: -0.0000

Data Index: 67993 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3589. Min Act: -0.0000

Data Index: 666216 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3583. Min Act: -0.0000

Data Index: 957528 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3358. Min Act: -0.0000

Data Index: 121146 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.3572. Min Act: -0.0000

Data Index: 638690 (C4 (Web Text))

Max Activating Token Index: 187