Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1052 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.7372. Min Act: -0.0001

Data Index: 936875 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.6457. Min Act: -0.0001

Data Index: 987674 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.5617. Min Act: -0.0001

Data Index: 375267 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.5678. Min Act: -0.0001

Data Index: 126205 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.6460. Min Act: -0.0001

Data Index: 492205 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.5330. Min Act: -0.0001

Data Index: 136072 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.5201. Min Act: -0.0001

Data Index: 1086124 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4779. Min Act: -0.0001

Data Index: 847886 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.5097. Min Act: -0.0001

Data Index: 23615 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3637. Min Act: -0.0001

Data Index: 173646 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4398. Min Act: -0.0001

Data Index: 767397 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.5609. Min Act: -0.0001

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3863. Min Act: -0.0001

Data Index: 865519 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4000. Min Act: -0.0001

Data Index: 649968 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3544. Min Act: -0.0001

Data Index: 38776 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4837. Min Act: -0.0001

Data Index: 1258070 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4763. Min Act: -0.0001

Data Index: 345905 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.3946. Min Act: -0.0001

Data Index: 1079590 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4289. Min Act: -0.0001

Data Index: 1130254 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.7372. Min Range: -1.7372

Max Act: 1.4349. Min Act: -0.0001

Data Index: 1256938 (C4 (Web Text))

Max Activating Token Index: 18