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

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

Neuron 5117 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1129. Min Act: -0.0001

Data Index: 930802 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0971. Min Act: -0.0001

Data Index: 842381 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1111241 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0908. Min Act: -0.0001

Data Index: 362095 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1246014 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0809. Min Act: -0.0001

Data Index: 415767 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0821. Min Act: -0.0001

Data Index: 842882 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1162677 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0739. Min Act: -0.0001

Data Index: 153296 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0738. Min Act: -0.0001

Data Index: 205393 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0736. Min Act: -0.0001

Data Index: 418466 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0701. Min Act: -0.0001

Data Index: 610549 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0648. Min Act: -0.0001

Data Index: 537620 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0645. Min Act: -0.0001

Data Index: 609503 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0644. Min Act: -0.0001

Data Index: 609240 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0664. Min Act: -0.0001

Data Index: 878436 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0573. Min Act: -0.0001

Data Index: 739473 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0639. Min Act: -0.0000

Data Index: 268400 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1201282 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1188903 (C4 (Web Text))

Max Activating Token Index: 626