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

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

Neuron 820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.9328. Min Act: -0.0000

Data Index: 611932 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.7153. Min Act: -0.0000

Data Index: 28765 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.6741. Min Act: -0.0000

Data Index: 678594 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.5264. Min Act: -0.0000

Data Index: 125705 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.5090. Min Act: -0.0000

Data Index: 954919 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.5119. Min Act: -0.0000

Data Index: 249805 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.4223. Min Act: -0.0000

Data Index: 171733 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.4157. Min Act: -0.0000

Data Index: 237829 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.4533. Min Act: -0.0000

Data Index: 537431 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.4274. Min Act: -0.0000

Data Index: 179988 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.5011. Min Act: -0.0000

Data Index: 326588 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.4051. Min Act: -0.0000

Data Index: 786299 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1117793 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.2852. Min Act: -0.0000

Data Index: 15054 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.3533. Min Act: -0.0000

Data Index: 432678 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.3571. Min Act: -0.0000

Data Index: 304893 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.3225. Min Act: -0.0000

Data Index: 807121 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1223008 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1084162 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.9328. Min Range: -1.9328

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1044129 (C4 (Web Text))

Max Activating Token Index: 743