Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3374 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.8136. Min Act: -0.0002

Data Index: 1297128 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7993. Min Act: -0.0003

Data Index: 600600 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7893. Min Act: -0.0002

Data Index: 628579 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7261. Min Act: -0.0002

Data Index: 273737 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7005. Min Act: -0.0002

Data Index: 580494 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7217. Min Act: -0.0002

Data Index: 50372 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6909. Min Act: -0.0002

Data Index: 856735 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.7287. Min Act: -0.0002

Data Index: 349582 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6317. Min Act: -0.0002

Data Index: 944085 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6304. Min Act: -0.0002

Data Index: 215266 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6420. Min Act: -0.0002

Data Index: 1258332 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6495. Min Act: -0.0002

Data Index: 123259 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6257. Min Act: -0.0002

Data Index: 754314 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6284. Min Act: -0.0002

Data Index: 666442 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6190. Min Act: -0.0002

Data Index: 1262062 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.6161. Min Act: -0.0002

Data Index: 1099920 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5812. Min Act: -0.0003

Data Index: 159697 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5882. Min Act: -0.0002

Data Index: 440640 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5881. Min Act: -0.0002

Data Index: 427907 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.8136. Min Range: -0.8136

Max Act: 0.5512. Min Act: -0.0002

Data Index: 1283277 (C4 (Web Text))

Max Activating Token Index: 438