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

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

Neuron 2075 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.7912. Min Act: -0.0001

Data Index: 680157 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3134. Min Act: -0.0001

Data Index: 269814 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.2380. Min Act: -0.0001

Data Index: 391829 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.2586. Min Act: -0.0001

Data Index: 958711 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.1979. Min Act: -0.0001

Data Index: 1316126 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.1334. Min Act: -0.0001

Data Index: 1110718 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.0857. Min Act: -0.0001

Data Index: 467638 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9911. Min Act: -0.0001

Data Index: 1196834 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.1158. Min Act: -0.0001

Data Index: 319479 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.0958. Min Act: -0.0001

Data Index: 1199657 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9750. Min Act: -0.0001

Data Index: 920468 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.0214. Min Act: -0.0001

Data Index: 476219 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9448. Min Act: -0.0001

Data Index: 391196 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9404. Min Act: -0.0001

Data Index: 937739 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9682. Min Act: -0.0001

Data Index: 833318 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9495. Min Act: -0.0001

Data Index: 219398 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9425. Min Act: -0.0001

Data Index: 945554 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9111. Min Act: -0.0001

Data Index: 103637 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9363. Min Act: -0.0001

Data Index: 643064 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.7912. Min Range: -1.7912

Max Act: 0.9333. Min Act: -0.0001

Data Index: 152697 (C4 (Web Text))

Max Activating Token Index: 980