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

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

Neuron 32 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1022015 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5370. Min Act: -0.0000

Data Index: 466832 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5657. Min Act: -0.0000

Data Index: 765913 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5249. Min Act: -0.0000

Data Index: 127449 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1346512 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1255341 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4769. Min Act: -0.0000

Data Index: 243210 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1289667 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1058255 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1226312 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4309. Min Act: -0.0000

Data Index: 589671 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4220. Min Act: -0.0000

Data Index: 155324 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1156503 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1234605 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4156. Min Act: -0.0000

Data Index: 39699 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4835. Min Act: -0.0000

Data Index: 350007 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4659. Min Act: -0.0000

Data Index: 656939 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1238286 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4332. Min Act: -0.0000

Data Index: 818482 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4424. Min Act: -0.0000

Data Index: 434545 (C4 (Web Text))

Max Activating Token Index: 320