Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0556. Min Range: -2.0556

Max Act: 2.0556. Min Act: -0.0000

Data Index: 675831 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.7934. Min Act: -0.0000

Data Index: 443748 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.6159. Min Act: -0.0000

Data Index: 796798 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.6306. Min Act: -0.0000

Data Index: 22241 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.6090. Min Act: -0.0000

Data Index: 115209 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.5861. Min Act: -0.0001

Data Index: 1338387 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.5498. Min Act: -0.0001

Data Index: 849352 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.4980. Min Act: -0.0000

Data Index: 719439 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.5324. Min Act: -0.0000

Data Index: 744525 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.5224. Min Act: -0.0000

Data Index: 529126 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.5338. Min Act: -0.0000

Data Index: 765458 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.5281. Min Act: -0.0000

Data Index: 1032696 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.3996. Min Act: -0.0000

Data Index: 188127 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.4687. Min Act: -0.0000

Data Index: 965041 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.4262. Min Act: -0.0000

Data Index: 1345038 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.4125. Min Act: -0.0000

Data Index: 668527 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.4346. Min Act: -0.0000

Data Index: 54587 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1005351 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.3809. Min Act: -0.0001

Data Index: 951297 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 2.0556. Min Range: -2.0556

Max Act: 1.3798. Min Act: -0.0000

Data Index: 343130 (C4 (Web Text))

Max Activating Token Index: 552