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

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

Neuron 4830 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: 2.1126. Min Range: -2.1126

Max Act: 2.1126. Min Act: -0.0000

Data Index: 1202553 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.9149. Min Act: -0.0000

Data Index: 870964 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1265532 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.7171. Min Act: -0.0000

Data Index: 1300074 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.6977. Min Act: -0.0000

Data Index: 243065 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5541. Min Act: -0.0000

Data Index: 749601 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.6354. Min Act: -0.0000

Data Index: 766608 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5418. Min Act: -0.0000

Data Index: 727429 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.6036. Min Act: -0.0000

Data Index: 424099 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.6869. Min Act: -0.0000

Data Index: 1011448 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5722. Min Act: -0.0000

Data Index: 1004766 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5857. Min Act: -0.0000

Data Index: 376556 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1098718 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5743. Min Act: -0.0000

Data Index: 477691 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5265. Min Act: -0.0000

Data Index: 922843 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.4332. Min Act: -0.0000

Data Index: 662686 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5205. Min Act: -0.0000

Data Index: 1356506 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.3373. Min Act: -0.0000

Data Index: 1010318 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1058877 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 2.1126. Min Range: -2.1126

Max Act: 1.5033. Min Act: -0.0000

Data Index: 48557 (C4 (Web Text))

Max Activating Token Index: 32