Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1401 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0285. Min Act: -0.0006

Data Index: 134407 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0278. Min Act: -0.0006

Data Index: 375882 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1173610 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0266. Min Act: -0.0006

Data Index: 885209 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1099525 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0272. Min Act: -0.0006

Data Index: 529920 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0267. Min Act: -0.0006

Data Index: 62148 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1239272 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0272. Min Act: -0.0006

Data Index: 957735 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0267. Min Act: -0.0006

Data Index: 537407 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1233136 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0260. Min Act: -0.0006

Data Index: 996934 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0261. Min Act: -0.0006

Data Index: 395448 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0256. Min Act: -0.0006

Data Index: 948810 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0260. Min Act: -0.0006

Data Index: 659649 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0260. Min Act: -0.0006

Data Index: 889152 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0248. Min Act: -0.0006

Data Index: 272143 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0268. Min Act: -0.0006

Data Index: 758514 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0256. Min Act: -0.0006

Data Index: 890973 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0286. Min Range: -0.0286

Max Act: 0.0251. Min Act: -0.0006

Data Index: 939839 (C4 (Web Text))

Max Activating Token Index: 565