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

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

Neuron 5039 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1413213 (Python Code)

Max Activating Token Index: 651

Text #1

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5310. Min Act: -0.0000

Data Index: 468968 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3129. Min Act: -0.0000

Data Index: 430164 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4765. Min Act: -0.0000

Data Index: 651776 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5140. Min Act: -0.0000

Data Index: 1010320 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4099. Min Act: -0.0000

Data Index: 978841 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1270153 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1655962 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.0691. Min Act: -0.0000

Data Index: 822578 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.9947. Min Act: -0.0000

Data Index: 85538 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1580766 (Python Code)

Max Activating Token Index: 781

Text #11

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.9734. Min Act: -0.0000

Data Index: 45942 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1376683 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1429248 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1493982 (Python Code)

Max Activating Token Index: 564

Text #15

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1477915 (Python Code)

Max Activating Token Index: 703

Text #16

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.8197. Min Act: -0.0000

Data Index: 348416 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1398761 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.7628. Min Act: -0.0000

Data Index: 583854 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 1.5457. Min Range: -1.5457

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1646426 (Python Code)

Max Activating Token Index: 301