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

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

Neuron 4698 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1006258 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0002

Data Index: 593154 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1513376 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1448580 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1419883 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1171946 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1576764 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0070. Min Act: -0.0002

Data Index: 411855 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1083576 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1566924 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1625455 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1480398 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1578530 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1096291 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0065. Min Act: -0.0002

Data Index: 501854 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1236620 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1626520 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0064. Min Act: -0.0002

Data Index: 867593 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1140007 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1097638 (C4 (Web Text))

Max Activating Token Index: 4