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

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

Neuron 5087 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4710. Min Act: -0.0000

Data Index: 722202 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1000293 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1600280 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3346. Min Act: -0.0000

Data Index: 617888 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3669. Min Act: -0.0000

Data Index: 139456 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1656325 (Python Code)

Max Activating Token Index: 392

Text #6

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3649. Min Act: -0.0000

Data Index: 730301 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3312. Min Act: -0.0000

Data Index: 806301 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1455581 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1271644 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1315680 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2772. Min Act: -0.0000

Data Index: 385490 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2999. Min Act: -0.0000

Data Index: 649601 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2816. Min Act: -0.0000

Data Index: 525642 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2708. Min Act: -0.0000

Data Index: 894469 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3313. Min Act: -0.0000

Data Index: 409170 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1567173 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2890. Min Act: -0.0000

Data Index: 167737 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1582019 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1386485 (Python Code)

Max Activating Token Index: 881