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

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

Neuron 3560 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: 0.3663. Min Range: -0.3663

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1225451 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1292431 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3278. Min Act: -0.0001

Data Index: 601349 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3056. Min Act: -0.0000

Data Index: 426763 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2685. Min Act: -0.0001

Data Index: 1351351 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2897. Min Act: -0.0001

Data Index: 880781 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2749. Min Act: -0.0000

Data Index: 869103 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2980. Min Act: -0.0001

Data Index: 1306874 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2620. Min Act: -0.0000

Data Index: 933009 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2564. Min Act: -0.0001

Data Index: 810300 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2665. Min Act: -0.0001

Data Index: 195715 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2583. Min Act: -0.0000

Data Index: 764980 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2746. Min Act: -0.0000

Data Index: 635519 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2441. Min Act: -0.0000

Data Index: 270052 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1270058 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2493. Min Act: -0.0000

Data Index: 695344 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2561. Min Act: -0.0001

Data Index: 242786 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1146766 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1300098 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.2377. Min Act: -0.0001

Data Index: 602485 (C4 (Web Text))

Max Activating Token Index: 457