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

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

Neuron 3230 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7532. Min Act: -0.0000

Data Index: 77733 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7001. Min Act: -0.0000

Data Index: 634078 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6423. Min Act: -0.0000

Data Index: 176470 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5806. Min Act: -0.0000

Data Index: 373978 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5558. Min Act: -0.0000

Data Index: 660053 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6029. Min Act: -0.0000

Data Index: 81193 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1116856 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5846. Min Act: -0.0000

Data Index: 852901 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5697. Min Act: -0.0000

Data Index: 885074 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4971. Min Act: -0.0000

Data Index: 57310 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1076146 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1182219 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5768. Min Act: -0.0000

Data Index: 737853 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5275. Min Act: -0.0000

Data Index: 574079 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1135055 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5776. Min Act: -0.0000

Data Index: 84751 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4658. Min Act: -0.0000

Data Index: 886707 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5236. Min Act: -0.0000

Data Index: 656936 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5002. Min Act: -0.0000

Data Index: 634029 (C4 (Web Text))

Max Activating Token Index: 684