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

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

Neuron 498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.4174. Min Act: -0.0000

Data Index: 359014 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.3843. Min Act: -0.0000

Data Index: 882764 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.4593. Min Act: -0.0000

Data Index: 752579 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1303695 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1019893 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2786. Min Act: -0.0000

Data Index: 863985 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2735. Min Act: -0.0000

Data Index: 179199 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2462. Min Act: -0.0000

Data Index: 1255766 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2514. Min Act: -0.0000

Data Index: 179425 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.3227. Min Act: -0.0000

Data Index: 750831 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2309. Min Act: -0.0000

Data Index: 306250 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2073. Min Act: -0.0000

Data Index: 616765 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2107. Min Act: -0.0000

Data Index: 964991 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2722. Min Act: -0.0000

Data Index: 800904 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1053460 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1238225 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1076744 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1027. Min Act: -0.0000

Data Index: 577401 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.1731. Min Act: -0.0000

Data Index: 401359 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.4593. Min Range: -1.4593

Max Act: 1.2284. Min Act: -0.0000

Data Index: 1333431 (C4 (Web Text))

Max Activating Token Index: 933