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

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

Neuron 906 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: 0.0057. Min Range: -0.0057

Max Act: 0.0057. Min Act: -0.0006

Data Index: 982429 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1177644 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1252151 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0006

Data Index: 136328 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0006

Data Index: 810199 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1014417 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0005

Data Index: 533588 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0006

Data Index: 726405 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0006

Data Index: 279368 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1319736 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 461783 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 880324 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0006

Data Index: 296808 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0053. Min Act: -0.0006

Data Index: 777031 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0052. Min Act: -0.0006

Data Index: 991355 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0006

Data Index: 875687 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1059177 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0006

Data Index: 787440 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0051. Min Act: -0.0006

Data Index: 318341 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.0057. Min Range: -0.0057

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1082296 (C4 (Web Text))

Max Activating Token Index: 521