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

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

Neuron 2835 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: 0.6095. Min Range: -0.6095

Max Act: 0.6095. Min Act: -0.0000

Data Index: 247648 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5784. Min Act: -0.0000

Data Index: 573883 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5560. Min Act: -0.0000

Data Index: 560123 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4602. Min Act: 0.0000

Data Index: 1124045 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1342138 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4025. Min Act: 0.0000

Data Index: 598633 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4121. Min Act: 0.0001

Data Index: 592706 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4119. Min Act: -0.0000

Data Index: 156265 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3650. Min Act: -0.0000

Data Index: 407543 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3972. Min Act: 0.0001

Data Index: 496868 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3908. Min Act: -0.0000

Data Index: 119381 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1061388 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1277677 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3788. Min Act: -0.0000

Data Index: 59681 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3659. Min Act: -0.0000

Data Index: 525148 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3625. Min Act: -0.0000

Data Index: 39714 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3404. Min Act: -0.0000

Data Index: 400575 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1331051 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3617. Min Act: -0.0000

Data Index: 844630 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.3368. Min Act: -0.0000

Data Index: 335972 (C4 (Web Text))

Max Activating Token Index: 645