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

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

Neuron 1650 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: 0.9278. Min Range: -0.9278

Max Act: 0.9278. Min Act: -0.0000

Data Index: 684327 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8844. Min Act: -0.0000

Data Index: 119191 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8503. Min Act: -0.0000

Data Index: 509390 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8663. Min Act: -0.0000

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8862. Min Act: -0.0000

Data Index: 31859 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7829. Min Act: -0.0000

Data Index: 296780 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.8111. Min Act: -0.0000

Data Index: 52125 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7314. Min Act: -0.0000

Data Index: 440470 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.6564. Min Act: -0.0000

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.6784. Min Act: -0.0000

Data Index: 493344 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7227. Min Act: -0.0000

Data Index: 370237 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7124. Min Act: -0.0000

Data Index: 720897 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1033122 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.6808. Min Act: -0.0000

Data Index: 766289 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.5802. Min Act: -0.0000

Data Index: 683814 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.5899. Min Act: -0.0000

Data Index: 961158 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.5789. Min Act: -0.0000

Data Index: 256108 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.5756. Min Act: -0.0000

Data Index: 211750 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.9278. Min Range: -0.9278

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1321295 (C4 (Web Text))

Max Activating Token Index: 954