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

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

Neuron 776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4996. Min Act: -0.0001

Data Index: 357683 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4716. Min Act: -0.0000

Data Index: 374657 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.5315. Min Act: -0.0000

Data Index: 336000 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1088759 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4880. Min Act: -0.0001

Data Index: 1067925 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4635. Min Act: -0.0001

Data Index: 69366 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4704. Min Act: -0.0001

Data Index: 218850 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4627. Min Act: -0.0001

Data Index: 760893 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4297. Min Act: -0.0001

Data Index: 412167 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4346. Min Act: -0.0001

Data Index: 299177 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4450. Min Act: -0.0000

Data Index: 931949 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4223. Min Act: -0.0001

Data Index: 987901 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4222. Min Act: -0.0000

Data Index: 186035 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1207815 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.3919. Min Act: -0.0001

Data Index: 84301 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4023. Min Act: -0.0001

Data Index: 25380 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1006941 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.3766. Min Act: -0.0000

Data Index: 66637 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.3874. Min Act: -0.0001

Data Index: 44559 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.3969. Min Act: -0.0000

Data Index: 840655 (C4 (Web Text))

Max Activating Token Index: 976