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

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

Neuron 4616 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: 3.0325. Min Range: -3.0325

Max Act: 3.0325. Min Act: -0.0000

Data Index: 1044266 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.7034. Min Act: -0.0000

Data Index: 945533 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.3966. Min Act: -0.0000

Data Index: 1053053 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.0736. Min Act: -0.0000

Data Index: 1075493 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.0557. Min Act: -0.0000

Data Index: 478192 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.0684. Min Act: -0.0000

Data Index: 9448 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.1534. Min Act: -0.0000

Data Index: 484815 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.2718. Min Act: -0.0000

Data Index: 143719 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.1366. Min Act: -0.0000

Data Index: 562450 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.1052. Min Act: -0.0000

Data Index: 385708 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.2974. Min Act: -0.0000

Data Index: 462533 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.0380. Min Act: -0.0000

Data Index: 485797 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 3.0325. Min Range: -3.0325

Max Act: 2.0035. Min Act: -0.0000

Data Index: 401844 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.9301. Min Act: -0.0000

Data Index: 959461 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.8003. Min Act: -0.0000

Data Index: 1145462 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.7829. Min Act: -0.0000

Data Index: 438217 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.9158. Min Act: -0.0000

Data Index: 1331967 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.5406. Min Act: -0.0000

Data Index: 1250675 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.5306. Min Act: -0.0000

Data Index: 115919 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.0325. Min Range: -3.0325

Max Act: 1.3856. Min Act: -0.0000

Data Index: 1345174 (C4 (Web Text))

Max Activating Token Index: 801