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

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

Neuron 2617 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1188431 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1466936 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6490. Min Act: -0.0000

Data Index: 87328 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6330. Min Act: -0.0000

Data Index: 398066 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1196845 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5614. Min Act: -0.0000

Data Index: 670155 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1180192 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1213690 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5899. Min Act: -0.0000

Data Index: 99392 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6154. Min Act: -0.0000

Data Index: 907103 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1257378 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5449. Min Act: 0.0000

Data Index: 560792 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5368. Min Act: -0.0000

Data Index: 803051 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1107434 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5486. Min Act: -0.0000

Data Index: 880989 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5448. Min Act: -0.0000

Data Index: 690456 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5240. Min Act: -0.0000

Data Index: 869745 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5182. Min Act: -0.0000

Data Index: 693504 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5101. Min Act: -0.0000

Data Index: 148860 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5195. Min Act: 0.0000

Data Index: 803746 (C4 (Web Text))

Max Activating Token Index: 86