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

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

Neuron 4459 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.3868. Min Act: -0.0000

Data Index: 302421 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.3762. Min Act: -0.0000

Data Index: 402863 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.3380. Min Act: -0.0000

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.3359. Min Act: -0.0000

Data Index: 76011 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1345899 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1289920 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2998. Min Act: -0.0000

Data Index: 855058 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2754. Min Act: -0.0000

Data Index: 155377 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2669. Min Act: -0.0000

Data Index: 134058 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2645. Min Act: -0.0000

Data Index: 993298 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2583. Min Act: -0.0000

Data Index: 256282 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2472. Min Act: -0.0000

Data Index: 346423 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2553. Min Act: -0.0000

Data Index: 997318 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2625. Min Act: -0.0000

Data Index: 202660 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2617. Min Act: -0.0000

Data Index: 677723 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2447. Min Act: -0.0000

Data Index: 848507 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2410. Min Act: -0.0000

Data Index: 948075 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2422. Min Act: -0.0000

Data Index: 13244 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.4741. Min Range: -0.4741

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1319274 (C4 (Web Text))

Max Activating Token Index: 125