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

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

Neuron 2090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2468. Min Range: -2.2468

Max Act: 2.2154. Min Act: -0.0000

Data Index: 243820 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.2468. Min Range: -2.2468

Max Act: 2.2468. Min Act: -0.0000

Data Index: 768567 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.9905. Min Act: -0.0000

Data Index: 357861 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.9858. Min Act: -0.0000

Data Index: 232012 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.7440. Min Act: -0.0000

Data Index: 550190 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.7364. Min Act: -0.0000

Data Index: 848015 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.7022. Min Act: -0.0000

Data Index: 553973 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1086378 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1337508 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.5239. Min Act: -0.0000

Data Index: 289518 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.5703. Min Act: -0.0000

Data Index: 749092 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1219652 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.4470. Min Act: -0.0000

Data Index: 894565 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.5291. Min Act: -0.0000

Data Index: 54317 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1247226 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.4584. Min Act: -0.0000

Data Index: 142931 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.4258. Min Act: -0.0000

Data Index: 693721 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.3405. Min Act: -0.0000

Data Index: 51488 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.2499. Min Act: -0.0000

Data Index: 696067 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 2.2468. Min Range: -2.2468

Max Act: 1.3655. Min Act: -0.0000

Data Index: 242718 (C4 (Web Text))

Max Activating Token Index: 993