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

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

Neuron 1005 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0001

Data Index: 575638 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1221472 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0871. Min Act: -0.0001

Data Index: 598968 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0875. Min Act: -0.0001

Data Index: 717364 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0899. Min Act: -0.0001

Data Index: 381899 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0784. Min Act: -0.0001

Data Index: 719522 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0795. Min Act: -0.0001

Data Index: 36437 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1319054 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0757. Min Act: -0.0001

Data Index: 222421 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1248638 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0751. Min Act: -0.0001

Data Index: 747419 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0776. Min Act: -0.0001

Data Index: 270770 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0766. Min Act: -0.0001

Data Index: 887359 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0744. Min Act: -0.0001

Data Index: 296245 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0752. Min Act: -0.0001

Data Index: 389586 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0726. Min Act: -0.0001

Data Index: 59119 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0769. Min Act: -0.0001

Data Index: 594869 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0678. Min Act: -0.0001

Data Index: 889366 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0731. Min Act: -0.0001

Data Index: 766667 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1260741 (C4 (Web Text))

Max Activating Token Index: 214