Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.5905. Min Act: -0.0000

Data Index: 752086 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.2714. Min Act: -0.0001

Data Index: 519504 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.3615. Min Act: -0.0000

Data Index: 615309 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.4117. Min Act: -0.0000

Data Index: 896385 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1130270 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.2555. Min Act: -0.0001

Data Index: 204005 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1796. Min Act: -0.0000

Data Index: 492978 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.2877. Min Act: -0.0001

Data Index: 1224892 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.3150. Min Act: -0.0000

Data Index: 493647 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.2037. Min Act: -0.0000

Data Index: 289768 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.3429. Min Act: -0.0001

Data Index: 656467 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1331. Min Act: -0.0001

Data Index: 722410 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.2033. Min Act: -0.0000

Data Index: 307858 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.2421. Min Act: -0.0001

Data Index: 476736 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1966. Min Act: -0.0001

Data Index: 35264 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1115411 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.0636. Min Act: -0.0000

Data Index: 147929 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1500. Min Act: -0.0001

Data Index: 705434 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1983. Min Act: -0.0000

Data Index: 889190 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.5905. Min Range: -1.5905

Max Act: 1.1513. Min Act: -0.0000

Data Index: 415653 (C4 (Web Text))

Max Activating Token Index: 52