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

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

Neuron 974 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: 0.0238. Min Range: -0.0238

Max Act: 0.0235. Min Act: -0.0006

Data Index: 861958 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1459045 (Python Code)

Max Activating Token Index: 729

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1448879 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1488191 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0224. Min Act: -0.0006

Data Index: 813297 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1640719 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1080634 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1626822 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0233. Min Act: -0.0006

Data Index: 652638 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1563558 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1609586 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0006

Data Index: 280287 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1354812 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1639386 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1393216 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1431090 (Python Code)

Max Activating Token Index: 834

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1496011 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1548325 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1619596 (Python Code)

Max Activating Token Index: 857

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1438315 (Python Code)

Max Activating Token Index: 163