Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0317. Min Range: -1.0317

Max Act: 1.0317. Min Act: -0.0001

Data Index: 465031 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.0317. Min Range: -1.0317

Max Act: 1.0131. Min Act: -0.0001

Data Index: 855043 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.9253. Min Act: -0.0001

Data Index: 1213393 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8769. Min Act: -0.0001

Data Index: 591136 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.9288. Min Act: -0.0001

Data Index: 478810 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.9118. Min Act: -0.0001

Data Index: 603248 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8536. Min Act: -0.0001

Data Index: 225796 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8620. Min Act: -0.0001

Data Index: 46074 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8251. Min Act: -0.0001

Data Index: 1215053 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8646. Min Act: -0.0001

Data Index: 26780 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8265. Min Act: -0.0001

Data Index: 1235168 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8487. Min Act: -0.0001

Data Index: 222658 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8102. Min Act: -0.0001

Data Index: 420289 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7996. Min Act: -0.0001

Data Index: 771992 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7481. Min Act: -0.0001

Data Index: 968437 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8285. Min Act: -0.0001

Data Index: 1162021 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8238. Min Act: -0.0001

Data Index: 809306 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.6836. Min Act: -0.0001

Data Index: 704304 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.8365. Min Act: -0.0001

Data Index: 1054310 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.0317. Min Range: -1.0317

Max Act: 0.7991. Min Act: -0.0001

Data Index: 106450 (C4 (Web Text))

Max Activating Token Index: 603