Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4615 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.7887. Min Act: -0.0000

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.6236. Min Act: -0.0000

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.4734. Min Act: -0.0000

Data Index: 615279 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.5149. Min Act: -0.0000

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.5834. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.3289. Min Act: -0.0000

Data Index: 496009 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 2.7887. Min Range: -2.7887

Max Act: 2.2812. Min Act: -0.0000

Data Index: 1117148 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.7701. Min Act: -0.0000

Data Index: 12801 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.5664. Min Act: -0.0000

Data Index: 963526 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.4571. Min Act: -0.0000

Data Index: 736499 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.3611. Min Act: -0.0000

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.4589. Min Act: -0.0000

Data Index: 949081 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.4459. Min Act: -0.0000

Data Index: 497294 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1159182 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.2299. Min Act: -0.0000

Data Index: 159552 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.3050. Min Act: -0.0000

Data Index: 503787 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.2910. Min Act: -0.0000

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.2852. Min Act: -0.0000

Data Index: 476949 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 2.7887. Min Range: -2.7887

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1073687 (C4 (Web Text))

Max Activating Token Index: 213