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

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

Neuron 3850 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6765. Min Act: -0.0000

Data Index: 1407441 (Python Code)

Max Activating Token Index: 254

Text #1

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1653749 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1486923 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1457291 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6000. Min Act: -0.0000

Data Index: 1399677 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1654021 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4340. Min Act: -0.0000

Data Index: 1413726 (Python Code)

Max Activating Token Index: 411

Text #7

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1477208 (Python Code)

Max Activating Token Index: 882

Text #8

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1619190 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1581694 (Python Code)

Max Activating Token Index: 135

Text #10

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1392104 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1612387 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1442298 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1368886 (Python Code)

Max Activating Token Index: 503

Text #14

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1652526 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1589555 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1436128 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1424344 (Python Code)

Max Activating Token Index: 857

Text #18

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1606599 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1440510 (Python Code)

Max Activating Token Index: 133