Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 859 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9323. Min Act: -0.0001

Data Index: 1314645 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9438. Min Act: -0.0001

Data Index: 341712 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1097231 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8448. Min Act: -0.0001

Data Index: 182582 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9587. Min Act: -0.0001

Data Index: 708804 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8040. Min Act: -0.0001

Data Index: 342408 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8111. Min Act: -0.0001

Data Index: 847155 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1211830 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1320175 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7548. Min Act: -0.0001

Data Index: 257396 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7463. Min Act: -0.0001

Data Index: 1227793 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7781. Min Act: -0.0001

Data Index: 326835 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7191. Min Act: -0.0001

Data Index: 232749 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7040. Min Act: -0.0001

Data Index: 1226959 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7024. Min Act: -0.0001

Data Index: 689707 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7433. Min Act: -0.0001

Data Index: 91314 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7382. Min Act: -0.0001

Data Index: 1354629 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1198048 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7081. Min Act: -0.0001

Data Index: 1046042 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7906. Min Act: -0.0001

Data Index: 702425 (C4 (Web Text))

Max Activating Token Index: 754