Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1548 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.7241. Min Act: -0.0000

Data Index: 583038 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.3812. Min Act: -0.0000

Data Index: 498893 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.2877. Min Act: -0.0000

Data Index: 136410 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.1857. Min Act: -0.0000

Data Index: 37924 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.2016. Min Act: -0.0000

Data Index: 183568 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.1167. Min Act: -0.0000

Data Index: 502237 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.1140. Min Act: -0.0000

Data Index: 309390 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.0139. Min Act: -0.0000

Data Index: 14975 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.0684. Min Act: -0.0000

Data Index: 192430 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1355992 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9700. Min Act: -0.0000

Data Index: 153554 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1130170 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.0180. Min Act: -0.0000

Data Index: 388565 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1169990 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9535. Min Act: -0.0000

Data Index: 598599 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.7241. Min Range: -1.7241

Max Act: 1.0237. Min Act: -0.0000

Data Index: 653682 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9464. Min Act: -0.0000

Data Index: 953200 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9402. Min Act: -0.0000

Data Index: 701608 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9898. Min Act: -0.0000

Data Index: 309069 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.7241. Min Range: -1.7241

Max Act: 0.9793. Min Act: -0.0000

Data Index: 826018 (C4 (Web Text))

Max Activating Token Index: 36