Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3941 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.0259. Min Range: -2.0259

Max Act: 2.0125. Min Act: -0.0002

Data Index: 408960 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 2.0259. Min Range: -2.0259

Max Act: 2.0200. Min Act: -0.0002

Data Index: 1061761 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 2.0259. Min Range: -2.0259

Max Act: 2.0259. Min Act: -0.0002

Data Index: 1295138 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.8735. Min Act: -0.0002

Data Index: 397987 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.8430. Min Act: -0.0002

Data Index: 319796 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.8552. Min Act: -0.0002

Data Index: 666475 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7435. Min Act: -0.0002

Data Index: 989988 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7698. Min Act: -0.0002

Data Index: 295723 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7880. Min Act: -0.0002

Data Index: 243756 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7768. Min Act: -0.0002

Data Index: 296902 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7108. Min Act: -0.0002

Data Index: 185112 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7175. Min Act: -0.0002

Data Index: 104586 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7312. Min Act: -0.0002

Data Index: 281188 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6954. Min Act: -0.0002

Data Index: 1155827 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6505. Min Act: -0.0002

Data Index: 405411 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7253. Min Act: -0.0002

Data Index: 293005 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6604. Min Act: -0.0002

Data Index: 995937 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.7279. Min Act: -0.0002

Data Index: 228719 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6976. Min Act: -0.0002

Data Index: 356817 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 2.0259. Min Range: -2.0259

Max Act: 1.6732. Min Act: -0.0002

Data Index: 474902 (C4 (Web Text))

Max Activating Token Index: 253