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

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

Neuron 5026 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1690. Min Act: -0.0000

Data Index: 565077 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1908. Min Act: -0.0000

Data Index: 326834 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.2259. Min Act: -0.0000

Data Index: 166571 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.1299. Min Act: -0.0000

Data Index: 843594 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0898. Min Act: -0.0000

Data Index: 713756 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9898. Min Act: -0.0000

Data Index: 83990 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0565. Min Act: -0.0000

Data Index: 925333 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9844. Min Act: -0.0000

Data Index: 919330 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9807. Min Act: -0.0000

Data Index: 318145 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0402. Min Act: -0.0000

Data Index: 798647 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0589. Min Act: -0.0000

Data Index: 766019 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0269. Min Act: -0.0000

Data Index: 678059 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0197. Min Act: -0.0000

Data Index: 908156 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9542. Min Act: -0.0000

Data Index: 452982 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.2259. Min Range: -1.2259

Max Act: 1.0188. Min Act: -0.0000

Data Index: 891945 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1194786 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1350834 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1301599 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9310. Min Act: -0.0000

Data Index: 574734 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.2259. Min Range: -1.2259

Max Act: 0.9326. Min Act: -0.0000

Data Index: 863967 (C4 (Web Text))

Max Activating Token Index: 45