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

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

Neuron 2590 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: 0.7436. Min Range: -0.7436

Max Act: 0.7436. Min Act: 0.0001

Data Index: 618790 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.6561. Min Act: 0.0000

Data Index: 452626 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5921. Min Act: 0.0001

Data Index: 924720 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5367. Min Act: 0.0000

Data Index: 1298913 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5646. Min Act: 0.0000

Data Index: 1276953 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5687. Min Act: 0.0002

Data Index: 1082426 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5496. Min Act: 0.0000

Data Index: 1357624 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5270. Min Act: 0.0001

Data Index: 226052 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5172. Min Act: 0.0003

Data Index: 677288 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5146. Min Act: 0.0000

Data Index: 276157 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4992. Min Act: -0.0000

Data Index: 427783 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.5372. Min Act: 0.0000

Data Index: 1191851 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4884. Min Act: 0.0002

Data Index: 433160 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4878. Min Act: 0.0000

Data Index: 1157412 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4941. Min Act: -0.0000

Data Index: 644612 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4677. Min Act: 0.0001

Data Index: 1353665 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4527. Min Act: 0.0000

Data Index: 384084 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4780. Min Act: 0.0000

Data Index: 1327481 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.7436. Min Range: -0.7436

Max Act: 0.4714. Min Act: -0.0000

Data Index: 656391 (C4 (Web Text))

Max Activating Token Index: 848