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

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

Neuron 1562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1312098 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7790. Min Act: -0.0000

Data Index: 609164 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1351294 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7137. Min Act: -0.0000

Data Index: 262559 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6977. Min Act: -0.0000

Data Index: 893476 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1337537 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6852. Min Act: -0.0000

Data Index: 887878 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6585. Min Act: -0.0000

Data Index: 439226 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6189. Min Act: -0.0000

Data Index: 504677 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6715. Min Act: -0.0000

Data Index: 767735 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7122. Min Act: -0.0000

Data Index: 21774 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6677. Min Act: -0.0000

Data Index: 167343 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.7225. Min Act: -0.0000

Data Index: 124160 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1060010 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6652. Min Act: -0.0000

Data Index: 75870 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1250838 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6760. Min Act: -0.0000

Data Index: 942762 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6564. Min Act: -0.0000

Data Index: 711506 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1038384 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.7790. Min Range: -0.7790

Max Act: 0.6375. Min Act: -0.0000

Data Index: 374898 (C4 (Web Text))

Max Activating Token Index: 637