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

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

Neuron 1016 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: 0.4263. Min Range: -0.4263

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1542788 (Python Code)

Max Activating Token Index: 389

Text #1

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1388636 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1382915 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1528605 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1566273 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1455349 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1428690 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1611136 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1414508 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1507161 (Python Code)

Max Activating Token Index: 223

Text #10

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1402092 (Python Code)

Max Activating Token Index: 196

Text #11

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2594. Min Act: -0.0000

Data Index: 1422939 (Python Code)

Max Activating Token Index: 777

Text #12

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1509146 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1481601 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1235378 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1383894 (Python Code)

Max Activating Token Index: 626

Text #16

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1390744 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1488247 (Python Code)

Max Activating Token Index: 976

Text #18

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1469910 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1406557 (Python Code)

Max Activating Token Index: 778