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

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

Neuron 1587 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: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0006

Data Index: 641947 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0320. Min Act: -0.0006

Data Index: 967628 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0285. Min Act: -0.0006

Data Index: 535953 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1161874 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0272. Min Act: -0.0006

Data Index: 132985 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1226977 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0255. Min Act: -0.0006

Data Index: 115541 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0249. Min Act: -0.0006

Data Index: 721157 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0265. Min Act: -0.0006

Data Index: 887743 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0254. Min Act: -0.0006

Data Index: 630453 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1312280 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1122634 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0253. Min Act: -0.0006

Data Index: 420393 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0006

Data Index: 26163 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0235. Min Act: -0.0006

Data Index: 21029 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0248. Min Act: -0.0006

Data Index: 727718 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0229. Min Act: -0.0006

Data Index: 987126 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0263. Min Act: -0.0006

Data Index: 419874 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0006

Data Index: 115184 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0252. Min Act: -0.0006

Data Index: 869106 (C4 (Web Text))

Max Activating Token Index: 322