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

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

Neuron 1587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7877. Min Act: -0.0001

Data Index: 694094 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7187. Min Act: -0.0001

Data Index: 628334 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.8127. Min Act: -0.0001

Data Index: 1085560 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7512. Min Act: -0.0002

Data Index: 717703 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7507. Min Act: -0.0002

Data Index: 161729 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7791. Min Act: -0.0002

Data Index: 686919 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7659. Min Act: -0.0001

Data Index: 264040 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7685. Min Act: -0.0002

Data Index: 1024631 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7379. Min Act: -0.0002

Data Index: 848810 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6810. Min Act: -0.0002

Data Index: 999900 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.5726. Min Act: -0.0002

Data Index: 1304010 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6816. Min Act: -0.0002

Data Index: 788846 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.7028. Min Act: -0.0001

Data Index: 817376 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6818. Min Act: -0.0001

Data Index: 1241239 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6505. Min Act: -0.0002

Data Index: 293498 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6102. Min Act: -0.0001

Data Index: 1136268 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6104. Min Act: -0.0002

Data Index: 112998 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6630. Min Act: -0.0002

Data Index: 421458 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6258. Min Act: -0.0002

Data Index: 1149249 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.8127. Min Range: -0.8127

Max Act: 0.6772. Min Act: -0.0002

Data Index: 1066396 (C4 (Web Text))

Max Activating Token Index: 1006