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

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

Neuron 424 in Layer 0

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: 84579 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0005

Data Index: 462965 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0006

Data Index: 623428 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0006

Data Index: 727671 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0006

Data Index: 935087 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1128656 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0006

Data Index: 509389 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1330014 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1262032 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0006

Data Index: 865698 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0006

Data Index: 1190655 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0006

Data Index: 702995 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0005

Data Index: 839414 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0048. Min Act: -0.0006

Data Index: 948583 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1028581 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0005

Data Index: 790930 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1157271 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0046. Min Act: -0.0006

Data Index: 523479 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0005

Data Index: 32522 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0047. Min Act: -0.0006

Data Index: 144524 (C4 (Web Text))

Max Activating Token Index: 250