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

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

Neuron 443 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1202213 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1358576 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3308. Min Act: -0.0000

Data Index: 102778 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1232050 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3124. Min Act: -0.0000

Data Index: 286059 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2931. Min Act: -0.0000

Data Index: 135777 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2628. Min Act: 0.0000

Data Index: 512647 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2586. Min Act: -0.0000

Data Index: 179879 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2457. Min Act: 0.0001

Data Index: 929787 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2579. Min Act: 0.0000

Data Index: 572934 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2367. Min Act: -0.0000

Data Index: 928026 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2392. Min Act: -0.0000

Data Index: 8700 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2355. Min Act: -0.0000

Data Index: 753140 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2224. Min Act: -0.0000

Data Index: 70854 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2200. Min Act: -0.0000

Data Index: 610149 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2248. Min Act: -0.0000

Data Index: 844063 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2204. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2118. Min Act: -0.0000

Data Index: 550058 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2199. Min Act: -0.0000

Data Index: 821562 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2160. Min Act: -0.0000

Data Index: 661875 (C4 (Web Text))

Max Activating Token Index: 642