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

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

Neuron 3747 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.3014. Min Act: -0.0000

Data Index: 964199 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2823. Min Act: -0.0000

Data Index: 61180 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2666. Min Act: -0.0000

Data Index: 663203 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2507. Min Act: -0.0001

Data Index: 319356 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2579. Min Act: -0.0000

Data Index: 933589 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1113683 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2370. Min Act: -0.0000

Data Index: 755800 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2372. Min Act: -0.0000

Data Index: 527581 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2496. Min Act: -0.0000

Data Index: 305036 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2418. Min Act: -0.0000

Data Index: 198672 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2378. Min Act: -0.0000

Data Index: 114311 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2178. Min Act: -0.0000

Data Index: 200470 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2203. Min Act: -0.0000

Data Index: 598913 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2197. Min Act: -0.0000

Data Index: 735898 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2265. Min Act: -0.0000

Data Index: 7616 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1342466 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2260. Min Act: -0.0001

Data Index: 601420 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2262. Min Act: -0.0000

Data Index: 330625 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2153. Min Act: -0.0000

Data Index: 771277 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2056. Min Act: -0.0000

Data Index: 842336 (C4 (Web Text))

Max Activating Token Index: 275