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

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

Neuron 1126 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1152487 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1503. Min Act: -0.0000

Data Index: 630283 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2051. Min Act: -0.0000

Data Index: 673754 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1190. Min Act: -0.0000

Data Index: 627968 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0851. Min Act: -0.0000

Data Index: 44623 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0686. Min Act: -0.0000

Data Index: 402998 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0587. Min Act: -0.0000

Data Index: 918685 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1011854 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9691. Min Act: -0.0000

Data Index: 928107 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9627. Min Act: -0.0000

Data Index: 807748 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1020242 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1093157 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8590. Min Act: -0.0000

Data Index: 873171 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.9055. Min Act: -0.0000

Data Index: 990030 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1137738 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1025174 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8814. Min Act: -0.0000

Data Index: 737692 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8445. Min Act: -0.0000

Data Index: 544537 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8470. Min Act: -0.0000

Data Index: 792838 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.2829. Min Range: -1.2829

Max Act: 0.8087. Min Act: -0.0000

Data Index: 870396 (C4 (Web Text))

Max Activating Token Index: 672