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

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

Neuron 4834 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.4447. Min Act: -0.0002

Data Index: 104260 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.2268. Min Act: -0.0002

Data Index: 293094 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.1769. Min Act: -0.0002

Data Index: 720623 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0683. Min Act: -0.0002

Data Index: 539408 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9084. Min Act: -0.0002

Data Index: 558960 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9592. Min Act: -0.0002

Data Index: 570435 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9704. Min Act: -0.0002

Data Index: 41148 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9783. Min Act: -0.0002

Data Index: 1338102 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0886. Min Act: -0.0002

Data Index: 178325 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9438. Min Act: -0.0002

Data Index: 1000758 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9338. Min Act: -0.0002

Data Index: 200270 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.4447. Min Range: -1.4447

Max Act: 1.0123. Min Act: -0.0002

Data Index: 1142360 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9373. Min Act: -0.0002

Data Index: 1182856 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.9386. Min Act: -0.0002

Data Index: 984947 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8768. Min Act: -0.0002

Data Index: 138447 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8719. Min Act: -0.0002

Data Index: 261743 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8881. Min Act: -0.0002

Data Index: 1188693 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8839. Min Act: -0.0002

Data Index: 472553 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8479. Min Act: -0.0002

Data Index: 35975 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.4447. Min Range: -1.4447

Max Act: 0.8325. Min Act: -0.0002

Data Index: 1122357 (C4 (Web Text))

Max Activating Token Index: 1003