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

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

Neuron 4891 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.5385. Min Act: -0.0000

Data Index: 903189 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.3673. Min Act: -0.0000

Data Index: 472382 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.2221. Min Act: -0.0000

Data Index: 979754 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1123842 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1106736 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0728. Min Act: -0.0000

Data Index: 601291 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.1172. Min Act: -0.0000

Data Index: 495827 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0449. Min Act: -0.0000

Data Index: 95359 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1223893 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1292885 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0229. Min Act: -0.0000

Data Index: 550276 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0581. Min Act: -0.0000

Data Index: 326425 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0270. Min Act: -0.0000

Data Index: 774661 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0156. Min Act: -0.0000

Data Index: 55384 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9534. Min Act: -0.0000

Data Index: 786201 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0186. Min Act: -0.0000

Data Index: 464756 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9427. Min Act: -0.0000

Data Index: 642808 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.5385. Min Range: -1.5385

Max Act: 0.9584. Min Act: -0.0000

Data Index: 261364 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0038. Min Act: -0.0000

Data Index: 928860 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.5385. Min Range: -1.5385

Max Act: 1.0591. Min Act: -0.0000

Data Index: 916986 (C4 (Web Text))

Max Activating Token Index: 543