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

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

Neuron 4434 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6919. Min Act: -0.0000

Data Index: 837118 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1241920 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1176637 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1296037 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6433. Min Act: -0.0000

Data Index: 372552 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6512. Min Act: -0.0000

Data Index: 411404 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.6165. Min Act: -0.0000

Data Index: 317933 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5706. Min Act: -0.0000

Data Index: 480373 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5908. Min Act: 0.0000

Data Index: 1117346 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5910. Min Act: -0.0000

Data Index: 607806 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5890. Min Act: -0.0000

Data Index: 40717 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1241725 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5407. Min Act: -0.0000

Data Index: 338208 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5632. Min Act: 0.0000

Data Index: 431992 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5532. Min Act: 0.0000

Data Index: 521808 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1220732 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5423. Min Act: -0.0000

Data Index: 825444 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5424. Min Act: -0.0000

Data Index: 793857 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1207398 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.6919. Min Range: -0.6919

Max Act: 0.5362. Min Act: -0.0000

Data Index: 401076 (C4 (Web Text))

Max Activating Token Index: 985