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

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

Neuron 3997 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: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0001

Data Index: 1510713 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1640169 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0002

Data Index: 94313 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1523633 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 540795 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 82600 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1056861 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1483714 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1602310 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0002

Data Index: 297978 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1618491 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1494725 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 893243 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0002

Data Index: 938621 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1402907 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0002

Data Index: 393502 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 806292 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0002

Data Index: 949747 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1115291 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 119732 (C4 (Web Text))

Max Activating Token Index: 481