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

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

Neuron 310 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1266934 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1308683 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1601288 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0002

Data Index: 630845 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0002

Data Index: 896665 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0003

Data Index: 403150 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0002

Data Index: 897791 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 827003 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1350165 (C4 (Web Text))

Max Activating Token Index: 0

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 6468 (C4 (Web Text))

Max Activating Token Index: 0

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 639371 (C4 (Web Text))

Max Activating Token Index: 0

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359841 (C4 (Web Text))

Max Activating Token Index: 0

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359843 (C4 (Web Text))

Max Activating Token Index: 0

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359844 (C4 (Web Text))

Max Activating Token Index: 0

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359842 (C4 (Web Text))

Max Activating Token Index: 0

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359840 (C4 (Web Text))

Max Activating Token Index: 0

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359853 (Python Code)

Max Activating Token Index: 0

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359854 (Python Code)

Max Activating Token Index: 0

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359858 (Python Code)

Max Activating Token Index: 0

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1359859 (Python Code)

Max Activating Token Index: 0