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

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

Neuron 64 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1424709 (Python Code)

Max Activating Token Index: 515

Text #1

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1401820 (Python Code)

Max Activating Token Index: 813

Text #2

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1523444 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.4303. Min Act: -0.0000

Data Index: 1477802 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1541879 (Python Code)

Max Activating Token Index: 544

Text #5

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1510518 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1412406 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1506081 (Python Code)

Max Activating Token Index: 956

Text #8

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1510072 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1603518 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1467692 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1553811 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1544636 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1414488 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1509018 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1419381 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1464618 (Python Code)

Max Activating Token Index: 898

Text #17

Max Range: 1.6718. Min Range: -1.6718

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1584578 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1532606 (Python Code)

Max Activating Token Index: 301

Text #19

Max Range: 1.6718. Min Range: -1.6718

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1377034 (Python Code)

Max Activating Token Index: 908