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

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

Neuron 3677 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.8777. Min Act: -0.0000

Data Index: 1189510 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.9319. Min Act: -0.0000

Data Index: 145860 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1586176 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1487082 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1367278 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.5612. Min Act: -0.0000

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1528813 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1633005 (Python Code)

Max Activating Token Index: 439

Text #9

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1519393 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1515797 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1460597 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.4194. Min Act: -0.0000

Data Index: 563926 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1553706 (Python Code)

Max Activating Token Index: 470

Text #14

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3740. Min Act: -0.0000

Data Index: 1420532 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.2812. Min Act: -0.0000

Data Index: 703229 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1398224 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1644172 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.2062. Min Act: -0.0000

Data Index: 1373154 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 1.9319. Min Range: -1.9319

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1524643 (Python Code)

Max Activating Token Index: 98