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

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

Neuron 2810 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: 0.5513. Min Range: -0.5513

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1283916 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5265. Min Act: -0.0000

Data Index: 706375 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5199. Min Act: -0.0000

Data Index: 797364 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5345. Min Act: -0.0000

Data Index: 642341 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1099714 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5008. Min Act: -0.0000

Data Index: 422125 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1272292 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5210. Min Act: -0.0000

Data Index: 411694 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4930. Min Act: -0.0000

Data Index: 190675 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4796. Min Act: -0.0000

Data Index: 263575 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1080248 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5011. Min Act: -0.0000

Data Index: 327530 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4744. Min Act: -0.0000

Data Index: 771447 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4852. Min Act: -0.0000

Data Index: 108315 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.5063. Min Act: -0.0000

Data Index: 253753 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4857. Min Act: -0.0000

Data Index: 17684 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4724. Min Act: -0.0000

Data Index: 56277 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4932. Min Act: -0.0000

Data Index: 72524 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1124153 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.5513. Min Range: -0.5513

Max Act: 0.4686. Min Act: -0.0000

Data Index: 836849 (C4 (Web Text))

Max Activating Token Index: 541