Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1978 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 9.1331. Min Range: -9.1331

Max Act: 9.1331. Min Act: -0.0001

Data Index: 635920 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 9.1331. Min Range: -9.1331

Max Act: 8.5627. Min Act: -0.0001

Data Index: 942996 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 9.1331. Min Range: -9.1331

Max Act: 8.3856. Min Act: -0.0001

Data Index: 1313402 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 9.1331. Min Range: -9.1331

Max Act: 8.4583. Min Act: -0.0001

Data Index: 857079 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.9727. Min Act: -0.0001

Data Index: 1007974 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 9.1331. Min Range: -9.1331

Max Act: 8.2183. Min Act: -0.0001

Data Index: 818729 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 9.1331. Min Range: -9.1331

Max Act: 8.0898. Min Act: -0.0001

Data Index: 277590 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.8795. Min Act: -0.0001

Data Index: 821665 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.7284. Min Act: -0.0001

Data Index: 955676 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.8740. Min Act: -0.0001

Data Index: 264168 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.9711. Min Act: -0.0001

Data Index: 1140052 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.5841. Min Act: -0.0001

Data Index: 462583 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.6721. Min Act: -0.0001

Data Index: 359519 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.4996. Min Act: -0.0001

Data Index: 853792 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.3785. Min Act: -0.0001

Data Index: 1192240 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.3305. Min Act: -0.0001

Data Index: 113051 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.1554. Min Act: -0.0001

Data Index: 899749 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.2646. Min Act: -0.0001

Data Index: 1202128 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.5635. Min Act: -0.0001

Data Index: 1246092 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 9.1331. Min Range: -9.1331

Max Act: 7.2070. Min Act: -0.0001

Data Index: 1324030 (C4 (Web Text))

Max Activating Token Index: 356