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

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

Neuron 101 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0238. Min Range: -5.0238

Max Act: 5.0238. Min Act: -0.0001

Data Index: 1277581 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.6230. Min Act: -0.0001

Data Index: 567440 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.1307. Min Act: -0.0001

Data Index: 1149029 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.0526. Min Act: -0.0001

Data Index: 1155205 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.0619. Min Act: -0.0001

Data Index: 900528 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.2014. Min Act: -0.0001

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.4750. Min Act: -0.0001

Data Index: 733279 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.1107. Min Act: -0.0001

Data Index: 253611 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.0747. Min Act: -0.0001

Data Index: 553687 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.8024. Min Act: -0.0001

Data Index: 1210609 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.0302. Min Act: -0.0001

Data Index: 1097221 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.8898. Min Act: -0.0001

Data Index: 1331392 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.8736. Min Act: -0.0001

Data Index: 29796 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.8482. Min Act: -0.0001

Data Index: 617548 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.8250. Min Act: -0.0001

Data Index: 138695 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 5.0238. Min Range: -5.0238

Max Act: 4.1327. Min Act: -0.0001

Data Index: 31320 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.7871. Min Act: -0.0001

Data Index: 562268 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.6153. Min Act: -0.0001

Data Index: 103263 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.9353. Min Act: -0.0001

Data Index: 38046 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 5.0238. Min Range: -5.0238

Max Act: 3.6054. Min Act: -0.0001

Data Index: 515471 (C4 (Web Text))

Max Activating Token Index: 698