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

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

Neuron 2175 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: 1.5854. Min Range: -1.5854

Max Act: 1.5854. Min Act: -0.0000

Data Index: 1322768 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.5002. Min Act: -0.0000

Data Index: 429824 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.2892. Min Act: -0.0000

Data Index: 452545 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.5189. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.2614. Min Act: -0.0000

Data Index: 133342 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.2910. Min Act: -0.0000

Data Index: 978570 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.1674. Min Act: -0.0000

Data Index: 604581 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.1120. Min Act: -0.0000

Data Index: 56704 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.2292. Min Act: -0.0000

Data Index: 796860 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.0168. Min Act: -0.0000

Data Index: 978602 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.5854. Min Range: -1.5854

Max Act: 1.0622. Min Act: -0.0000

Data Index: 807597 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9774. Min Act: -0.0000

Data Index: 580177 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9296. Min Act: -0.0000

Data Index: 653000 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9739. Min Act: -0.0000

Data Index: 348591 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9941. Min Act: -0.0000

Data Index: 204436 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9578. Min Act: -0.0000

Data Index: 859714 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9503. Min Act: -0.0000

Data Index: 939507 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.8879. Min Act: -0.0000

Data Index: 774547 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9386. Min Act: -0.0000

Data Index: 426458 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.5854. Min Range: -1.5854

Max Act: 0.9425. Min Act: -0.0000

Data Index: 715361 (C4 (Web Text))

Max Activating Token Index: 223