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

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

Neuron 2963 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: 0.1129. Min Range: -0.1129

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1645480 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1606256 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1581214 (Python Code)

Max Activating Token Index: 591

Text #3

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1498043 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1633939 (Python Code)

Max Activating Token Index: 120

Text #5

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1548786 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1561212 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1432048 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1589167 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1563830 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1631716 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1589527 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1382305 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1612457 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1442179 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1500028 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1510550 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1505145 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1428378 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1619057 (Python Code)

Max Activating Token Index: 205