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

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

Neuron 1470 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0954. Min Act: -0.0005

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0937. Min Act: -0.0005

Data Index: 1023106 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0962. Min Act: -0.0005

Data Index: 761512 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0969. Min Act: -0.0004

Data Index: 1063472 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0851. Min Act: -0.0004

Data Index: 492578 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0903. Min Act: -0.0005

Data Index: 1251812 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0869. Min Act: -0.0005

Data Index: 101285 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0856. Min Act: -0.0005

Data Index: 1179584 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0870. Min Act: -0.0005

Data Index: 410163 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0876. Min Act: -0.0005

Data Index: 271918 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0907. Min Act: -0.0004

Data Index: 1076221 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0868. Min Act: -0.0005

Data Index: 704102 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0834. Min Act: -0.0005

Data Index: 493402 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0901. Min Act: -0.0005

Data Index: 541153 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0857. Min Act: -0.0005

Data Index: 427419 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0896. Min Act: -0.0005

Data Index: 1267387 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0826. Min Act: -0.0005

Data Index: 625697 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0822. Min Act: -0.0005

Data Index: 307716 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0876. Min Act: -0.0005

Data Index: 287628 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0860. Min Act: -0.0004

Data Index: 1078393 (C4 (Web Text))

Max Activating Token Index: 473