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

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

Neuron 2661 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.0593. Min Act: -0.0000

Data Index: 1390354 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2787. Min Act: -0.0000

Data Index: 1377631 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1390560 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.3376. Min Act: -0.0000

Data Index: 1464487 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.1708. Min Act: -0.0000

Data Index: 171181 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2670. Min Act: -0.0000

Data Index: 1551562 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2692. Min Act: -0.0000

Data Index: 1436787 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2676. Min Act: -0.0000

Data Index: 1387832 (Python Code)

Max Activating Token Index: 517

Text #8

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2535. Min Act: -0.0000

Data Index: 1364544 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.1228. Min Act: -0.0000

Data Index: 1584010 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.0369. Min Act: -0.0000

Data Index: 1595084 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.1011. Min Act: -0.0000

Data Index: 1533001 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.1049. Min Act: -0.0000

Data Index: 1520803 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.0925. Min Act: -0.0000

Data Index: 1320047 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1437348 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 2.3376. Min Range: -2.3376

Max Act: 1.8207. Min Act: -0.0000

Data Index: 1367463 (Python Code)

Max Activating Token Index: 966

Text #16

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.0827. Min Act: -0.0000

Data Index: 1651117 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 2.3376. Min Range: -2.3376

Max Act: 1.8619. Min Act: -0.0000

Data Index: 1625905 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 2.3376. Min Range: -2.3376

Max Act: 1.9652. Min Act: -0.0000

Data Index: 1405726 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 2.3376. Min Range: -2.3376

Max Act: 2.2076. Min Act: -0.0000

Data Index: 1488270 (Python Code)

Max Activating Token Index: 335