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

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

Neuron 992 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: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1339064 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0866. Min Act: -0.0002

Data Index: 96441 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0866. Min Act: -0.0002

Data Index: 506543 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0863. Min Act: -0.0002

Data Index: 764667 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0868. Min Act: -0.0002

Data Index: 358029 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1041364 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1030386 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0816. Min Act: -0.0002

Data Index: 2938 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0796. Min Act: -0.0002

Data Index: 862069 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1093606 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0791. Min Act: -0.0002

Data Index: 270084 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0805. Min Act: -0.0002

Data Index: 335022 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0774. Min Act: -0.0002

Data Index: 817020 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0801. Min Act: -0.0002

Data Index: 120048 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1090192 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0743. Min Act: -0.0002

Data Index: 735916 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1086795 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0763. Min Act: -0.0002

Data Index: 539450 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0739. Min Act: -0.0002

Data Index: 34662 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0748. Min Act: -0.0002

Data Index: 914390 (C4 (Web Text))

Max Activating Token Index: 363