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

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

Neuron 2560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.6288. Min Act: -0.0000

Data Index: 1519795 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.5091. Min Act: -0.0000

Data Index: 78108 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.5020. Min Act: -0.0000

Data Index: 168196 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1576892 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.1823. Min Act: -0.0000

Data Index: 1619924 (Python Code)

Max Activating Token Index: 798

Text #5

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.3439. Min Act: -0.0000

Data Index: 1406328 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.1639. Min Act: -0.0000

Data Index: 1649867 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1530287 (Python Code)

Max Activating Token Index: 354

Text #8

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.0829. Min Act: -0.0000

Data Index: 1379751 (Python Code)

Max Activating Token Index: 695

Text #9

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1558985 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.0518. Min Act: -0.0000

Data Index: 1491984 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1392012 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.9565. Min Act: -0.0000

Data Index: 1573035 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.0487. Min Act: -0.0000

Data Index: 1643423 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.8590. Min Act: -0.0000

Data Index: 1370324 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.9584. Min Act: -0.0000

Data Index: 1612023 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 2.6288. Min Range: -2.6288

Max Act: 2.1447. Min Act: -0.0000

Data Index: 1288307 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.9338. Min Act: -0.0000

Data Index: 1498644 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.9207. Min Act: -0.0000

Data Index: 1069678 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.6288. Min Range: -2.6288

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1437783 (Python Code)

Max Activating Token Index: 220