Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1941 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.4023. Min Act: -0.0000

Data Index: 1329885 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.4523. Min Act: -0.0000

Data Index: 322275 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.3906. Min Act: -0.0000

Data Index: 814609 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.4193. Min Act: -0.0000

Data Index: 273575 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1045091 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1125254 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1082605 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1306322 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1431. Min Act: -0.0001

Data Index: 315640 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.2016. Min Act: -0.0000

Data Index: 83796 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1751. Min Act: -0.0000

Data Index: 748283 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1405. Min Act: -0.0000

Data Index: 729155 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1342873 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1882. Min Act: -0.0000

Data Index: 975473 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.2018. Min Act: -0.0000

Data Index: 548954 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1308. Min Act: -0.0001

Data Index: 591125 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1965. Min Act: -0.0000

Data Index: 476513 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1245. Min Act: -0.0000

Data Index: 311230 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1098654 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.4523. Min Range: -1.4523

Max Act: 1.0160. Min Act: -0.0001

Data Index: 343195 (C4 (Web Text))

Max Activating Token Index: 781