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

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

Neuron 4882 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: 1.8547. Min Range: -1.8547

Max Act: 1.8460. Min Act: -0.0001

Data Index: 192341 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7891. Min Act: -0.0000

Data Index: 470562 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.8547. Min Act: -0.0001

Data Index: 873169 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.7442. Min Act: -0.0001

Data Index: 527087 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1085641 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.3849. Min Act: -0.0001

Data Index: 1042611 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4324. Min Act: -0.0001

Data Index: 153720 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4295. Min Act: -0.0000

Data Index: 242215 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1222322 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.4158. Min Act: -0.0000

Data Index: 767053 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.3227. Min Act: -0.0001

Data Index: 68331 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.3827. Min Act: -0.0001

Data Index: 523088 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.3074. Min Act: -0.0001

Data Index: 204558 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.2318. Min Act: -0.0000

Data Index: 462541 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.2236. Min Act: -0.0001

Data Index: 738359 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.1695. Min Act: -0.0000

Data Index: 460289 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.1982. Min Act: -0.0001

Data Index: 230622 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.1714. Min Act: -0.0001

Data Index: 191722 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.2251. Min Act: -0.0001

Data Index: 979291 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.8547. Min Range: -1.8547

Max Act: 1.1736. Min Act: -0.0001

Data Index: 577899 (C4 (Web Text))

Max Activating Token Index: 880