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

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

Neuron 3460 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: 0.9996. Min Range: -0.9996

Max Act: 0.9996. Min Act: -0.0000

Data Index: 314126 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1356619 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8935. Min Act: -0.0000

Data Index: 858659 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8110. Min Act: -0.0000

Data Index: 111549 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8371. Min Act: -0.0000

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7781. Min Act: -0.0000

Data Index: 98332 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6847. Min Act: -0.0000

Data Index: 685381 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1026976 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6923. Min Act: -0.0000

Data Index: 621249 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7445. Min Act: -0.0000

Data Index: 944687 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1087348 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7435. Min Act: -0.0000

Data Index: 861309 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6595. Min Act: -0.0000

Data Index: 676513 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7260. Min Act: -0.0000

Data Index: 622854 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1121584 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1235824 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1284603 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6621. Min Act: -0.0000

Data Index: 887791 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6742. Min Act: -0.0000

Data Index: 88200 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6523. Min Act: -0.0000

Data Index: 53310 (C4 (Web Text))

Max Activating Token Index: 746