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

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

Neuron 3233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.1508. Min Act: -0.0000

Data Index: 916949 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.0585. Min Act: -0.0000

Data Index: 1338457 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7813. Min Act: -0.0000

Data Index: 460178 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7584. Min Act: -0.0000

Data Index: 672415 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1354615 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1237528 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1548707 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5599. Min Act: -0.0000

Data Index: 24790 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1333270 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1293310 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4405. Min Act: -0.0000

Data Index: 155945 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4713. Min Act: -0.0000

Data Index: 77113 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1025936 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5725. Min Act: -0.0000

Data Index: 504714 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5304. Min Act: -0.0000

Data Index: 548889 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3753. Min Act: -0.0000

Data Index: 178922 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3971. Min Act: -0.0000

Data Index: 748760 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.3381. Min Act: -0.0000

Data Index: 246687 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1538482 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4175. Min Act: -0.0000

Data Index: 852155 (C4 (Web Text))

Max Activating Token Index: 194