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

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

Neuron 5930 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5309. Min Range: -3.5309

Max Act: 3.5309. Min Act: -0.0001

Data Index: 1409674 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.7730. Min Act: -0.0000

Data Index: 1421573 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 3.5309. Min Range: -3.5309

Max Act: 3.1431. Min Act: -0.0001

Data Index: 1416694 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.5220. Min Act: -0.0001

Data Index: 1373632 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.4578. Min Act: -0.0001

Data Index: 1567593 (Python Code)

Max Activating Token Index: 183

Text #5

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.9790. Min Act: -0.0000

Data Index: 1415291 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.6222. Min Act: -0.0001

Data Index: 1590419 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.8534. Min Act: -0.0001

Data Index: 1609486 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.7151. Min Act: -0.0000

Data Index: 1510227 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.5737. Min Act: -0.0001

Data Index: 1371868 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.6053. Min Act: -0.0001

Data Index: 1413734 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.2125. Min Act: -0.0001

Data Index: 1395957 (Python Code)

Max Activating Token Index: 907

Text #12

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.3259. Min Act: -0.0001

Data Index: 1602462 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.5240. Min Act: -0.0001

Data Index: 1632328 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.1791. Min Act: -0.0001

Data Index: 1456557 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.3987. Min Act: -0.0000

Data Index: 1470517 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.6347. Min Act: -0.0001

Data Index: 1475729 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.7599. Min Act: -0.0001

Data Index: 1424283 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.4763. Min Act: -0.0001

Data Index: 1461096 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 3.5309. Min Range: -3.5309

Max Act: 2.4780. Min Act: -0.0001

Data Index: 1610115 (Python Code)

Max Activating Token Index: 678