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

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

Neuron 4331 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.2278. Min Act: -0.0001

Data Index: 125733 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.2247. Min Act: -0.0001

Data Index: 1230342 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1275275 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1344674 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1898. Min Act: -0.0001

Data Index: 228265 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1236776 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1935. Min Act: -0.0001

Data Index: 47401 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1991. Min Act: -0.0001

Data Index: 261304 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1730. Min Act: -0.0001

Data Index: 698975 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1952. Min Act: -0.0001

Data Index: 599161 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1659. Min Act: -0.0001

Data Index: 654929 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1849. Min Act: -0.0001

Data Index: 358390 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1348992 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1742. Min Act: -0.0001

Data Index: 774601 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1892. Min Act: -0.0001

Data Index: 476635 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1336952 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1711. Min Act: -0.0001

Data Index: 1061678 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1266697 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1934. Min Act: -0.0001

Data Index: 216948 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.2278. Min Range: -0.2278

Max Act: 0.1772. Min Act: -0.0001

Data Index: 499147 (C4 (Web Text))

Max Activating Token Index: 559