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

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

Neuron 795 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: 4.1263. Min Range: -4.1263

Max Act: 4.1263. Min Act: -0.0001

Data Index: 67191 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.7837. Min Act: -0.0001

Data Index: 986435 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.5817. Min Act: -0.0001

Data Index: 642798 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.4896. Min Act: -0.0001

Data Index: 908728 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.3382. Min Act: -0.0001

Data Index: 724612 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.1561. Min Act: -0.0001

Data Index: 341768 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.4475. Min Act: -0.0001

Data Index: 1156934 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.1154. Min Act: -0.0001

Data Index: 21642 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.5565. Min Act: -0.0001

Data Index: 687352 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.4021. Min Act: -0.0001

Data Index: 394754 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.2352. Min Act: -0.0001

Data Index: 844016 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.5176. Min Act: -0.0001

Data Index: 1266045 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.3565. Min Act: -0.0001

Data Index: 1184002 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.1460. Min Act: -0.0001

Data Index: 857164 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.1428. Min Act: -0.0001

Data Index: 296661 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.2778. Min Act: -0.0001

Data Index: 41515 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.2469. Min Act: -0.0001

Data Index: 115306 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.1895. Min Act: -0.0001

Data Index: 692415 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.1900. Min Act: -0.0001

Data Index: 407375 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 4.1263. Min Range: -4.1263

Max Act: 3.0239. Min Act: -0.0001

Data Index: 406645 (C4 (Web Text))

Max Activating Token Index: 822