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

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

Neuron 4820 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8381. Min Range: -8.8381

Max Act: 8.8381. Min Act: -0.0000

Data Index: 1611420 (Python Code)

Max Activating Token Index: 728

Text #1

Max Range: 8.8381. Min Range: -8.8381

Max Act: 4.3378. Min Act: -0.0000

Data Index: 452786 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.5339. Min Act: -0.0000

Data Index: 137584 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.4699. Min Act: -0.0000

Data Index: 1455250 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.6944. Min Act: -0.0000

Data Index: 1602930 (Python Code)

Max Activating Token Index: 278

Text #5

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1522198 (Python Code)

Max Activating Token Index: 393

Text #6

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.3857. Min Act: -0.0000

Data Index: 1560577 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.1377. Min Act: -0.0000

Data Index: 1574673 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1577230 (Python Code)

Max Activating Token Index: 197

Text #9

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.1930. Min Act: -0.0000

Data Index: 1423944 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 8.8381. Min Range: -8.8381

Max Act: 1.8831. Min Act: -0.0000

Data Index: 1622883 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 8.8381. Min Range: -8.8381

Max Act: 1.9656. Min Act: -0.0000

Data Index: 1477795 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 8.8381. Min Range: -8.8381

Max Act: 1.7428. Min Act: -0.0000

Data Index: 1431623 (Python Code)

Max Activating Token Index: 276

Text #13

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.1816. Min Act: -0.0000

Data Index: 1600963 (Python Code)

Max Activating Token Index: 545

Text #14

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.0562. Min Act: -0.0000

Data Index: 1467010 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.2753. Min Act: -0.0000

Data Index: 1430861 (Python Code)

Max Activating Token Index: 994

Text #16

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.0314. Min Act: -0.0000

Data Index: 1373093 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.0310. Min Act: -0.0000

Data Index: 1539970 (Python Code)

Max Activating Token Index: 937

Text #18

Max Range: 8.8381. Min Range: -8.8381

Max Act: 2.1008. Min Act: -0.0000

Data Index: 1424532 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 8.8381. Min Range: -8.8381

Max Act: 1.8740. Min Act: -0.0000

Data Index: 1555462 (Python Code)

Max Activating Token Index: 298