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

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

Neuron 2532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.4180. Min Act: -0.0000

Data Index: 104647 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1219850 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.2840. Min Act: -0.0000

Data Index: 639698 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.1481. Min Act: -0.0000

Data Index: 467726 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1213488 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0664. Min Act: -0.0000

Data Index: 208932 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9213. Min Act: -0.0000

Data Index: 526403 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9164. Min Act: -0.0000

Data Index: 918039 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1287533 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1357797 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9628. Min Act: -0.0000

Data Index: 786291 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1020128 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0217. Min Act: -0.0000

Data Index: 149128 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9477. Min Act: -0.0000

Data Index: 407696 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1329834 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9244. Min Act: -0.0000

Data Index: 842887 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.8475. Min Act: -0.0000

Data Index: 641590 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1184904 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.8955. Min Act: -0.0000

Data Index: 247165 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.4180. Min Range: -1.4180

Max Act: 0.9473. Min Act: -0.0000

Data Index: 548123 (C4 (Web Text))

Max Activating Token Index: 650