Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 732 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0006

Data Index: 962306 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 889570 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0006

Data Index: 299069 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0006

Data Index: 386495 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1161833 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0005

Data Index: 561112 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1499971 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1577922 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1652005 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1612844 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1559175 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0046. Min Act: -0.0006

Data Index: 416463 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1413359 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 93696 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1413887 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0040. Min Act: -0.0006

Data Index: 1238701 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1427491 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0045. Min Act: -0.0006

Data Index: 371519 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0046. Min Act: -0.0006

Data Index: 164222 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0041. Min Act: -0.0006

Data Index: 1385656 (Python Code)

Max Activating Token Index: 412