Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5908 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.2153. Min Act: -0.0000

Data Index: 586244 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.2763. Min Act: -0.0000

Data Index: 224108 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1577. Min Act: -0.0000

Data Index: 898611 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0063. Min Act: -0.0000

Data Index: 880197 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0766. Min Act: -0.0000

Data Index: 44533 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1089183 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1541. Min Act: -0.0000

Data Index: 15546 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1527978 (Python Code)

Max Activating Token Index: 529

Text #8

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1552627 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9965. Min Act: -0.0000

Data Index: 706076 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0248. Min Act: -0.0000

Data Index: 435315 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1485834 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9911. Min Act: -0.0000

Data Index: 617442 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0448. Min Act: -0.0000

Data Index: 863135 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1223734 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1405438 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1314803 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9546. Min Act: -0.0000

Data Index: 181585 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8447. Min Act: -0.0000

Data Index: 750717 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9510. Min Act: -0.0000

Data Index: 700870 (C4 (Web Text))

Max Activating Token Index: 364