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

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

Neuron 3814 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: 0.9501. Min Range: -0.9501

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1177841 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9428. Min Act: -0.0000

Data Index: 789060 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9036. Min Act: -0.0000

Data Index: 282006 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9087. Min Act: -0.0000

Data Index: 766484 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1040812 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8502. Min Act: -0.0000

Data Index: 351179 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8139. Min Act: -0.0000

Data Index: 515667 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1303755 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8038. Min Act: -0.0000

Data Index: 897339 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1028940 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1300618 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1342824 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1032666 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6929. Min Act: -0.0000

Data Index: 36683 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6368. Min Act: -0.0000

Data Index: 305413 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1206147 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6682. Min Act: -0.0000

Data Index: 505869 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1013561 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6159. Min Act: -0.0000

Data Index: 743930 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6079. Min Act: -0.0000

Data Index: 332689 (C4 (Web Text))

Max Activating Token Index: 506