Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1524 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0000

Data Index: 561258 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0685. Min Act: -0.0002

Data Index: 589407 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0677. Min Act: -0.0002

Data Index: 649600 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1333238 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1092145 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0657. Min Act: -0.0001

Data Index: 449690 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0661. Min Act: -0.0002

Data Index: 712337 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0630. Min Act: -0.0002

Data Index: 270580 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1331154 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0602. Min Act: -0.0002

Data Index: 348286 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0611. Min Act: -0.0001

Data Index: 517820 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0601. Min Act: -0.0001

Data Index: 894883 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0597. Min Act: -0.0000

Data Index: 151617 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0596. Min Act: -0.0002

Data Index: 881633 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0580. Min Act: -0.0002

Data Index: 718384 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0593. Min Act: -0.0002

Data Index: 608723 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0591. Min Act: -0.0001

Data Index: 91897 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0597. Min Act: -0.0001

Data Index: 716872 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1198979 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0583. Min Act: -0.0002

Data Index: 194919 (C4 (Web Text))

Max Activating Token Index: 244