Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1405 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0729. Min Act: -0.0001

Data Index: 1038426 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9941. Min Act: -0.0001

Data Index: 274064 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0068. Min Act: -0.0002

Data Index: 604760 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0842. Min Act: -0.0002

Data Index: 95968 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9196. Min Act: -0.0001

Data Index: 816377 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0370. Min Act: -0.0001

Data Index: 906441 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.0842. Min Range: -1.0842

Max Act: 1.0070. Min Act: -0.0002

Data Index: 636637 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.7843. Min Act: -0.0002

Data Index: 1271088 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.9000. Min Act: -0.0001

Data Index: 485145 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8737. Min Act: -0.0002

Data Index: 855934 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8623. Min Act: -0.0002

Data Index: 319888 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8775. Min Act: -0.0002

Data Index: 165045 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8789. Min Act: -0.0002

Data Index: 687635 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8355. Min Act: -0.0001

Data Index: 450445 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8285. Min Act: -0.0001

Data Index: 41416 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.7976. Min Act: -0.0002

Data Index: 350605 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8288. Min Act: -0.0001

Data Index: 573174 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8120. Min Act: -0.0002

Data Index: 896760 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.7458. Min Act: -0.0001

Data Index: 675784 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.0842. Min Range: -1.0842

Max Act: 0.8104. Min Act: -0.0002

Data Index: 957403 (C4 (Web Text))

Max Activating Token Index: 713