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

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

Neuron 4795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.1325. Min Act: -0.0000

Data Index: 414236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9257. Min Act: -0.0000

Data Index: 116459 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0198. Min Act: -0.0000

Data Index: 37545 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7824. Min Act: -0.0000

Data Index: 259808 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9352. Min Act: -0.0000

Data Index: 829636 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7687. Min Act: -0.0000

Data Index: 544101 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 3.1325. Min Range: -3.1325

Max Act: 3.0148. Min Act: -0.0000

Data Index: 845213 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7575. Min Act: -0.0000

Data Index: 1304402 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.6667. Min Act: -0.0000

Data Index: 562391 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7905. Min Act: -0.0000

Data Index: 1238454 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9248. Min Act: -0.0000

Data Index: 1006907 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.6591. Min Act: -0.0000

Data Index: 228438 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7893. Min Act: -0.0000

Data Index: 1084749 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.6525. Min Act: -0.0000

Data Index: 514964 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.9145. Min Act: -0.0000

Data Index: 1223756 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7707. Min Act: -0.0000

Data Index: 495347 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.7737. Min Act: -0.0000

Data Index: 212454 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.6351. Min Act: -0.0000

Data Index: 188303 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.6192. Min Act: -0.0000

Data Index: 969845 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.1325. Min Range: -3.1325

Max Act: 2.6720. Min Act: -0.0000

Data Index: 954450 (C4 (Web Text))

Max Activating Token Index: 155