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

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

Neuron 4964 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1505. Min Act: -0.0002

Data Index: 981659 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0002

Data Index: 660039 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1488. Min Act: -0.0002

Data Index: 1084930 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1427. Min Act: -0.0002

Data Index: 917200 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0840. Min Act: -0.0002

Data Index: 658987 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1097725 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1191. Min Act: -0.0002

Data Index: 237462 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1059994 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1185. Min Act: -0.0002

Data Index: 769377 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1005. Min Act: -0.0002

Data Index: 851655 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1106. Min Act: -0.0002

Data Index: 656748 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1076606 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1101. Min Act: -0.0002

Data Index: 575355 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1421331 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1016. Min Act: -0.0002

Data Index: 832214 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0973. Min Act: -0.0002

Data Index: 1284522 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1375904 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0904. Min Act: -0.0002

Data Index: 133019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1219521 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1017. Min Act: -0.0002

Data Index: 586372 (C4 (Web Text))

Max Activating Token Index: 224