Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3970 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.4008. Min Act: -0.0001

Data Index: 323774 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3986. Min Act: -0.0001

Data Index: 852265 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3646. Min Act: -0.0001

Data Index: 422073 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3619. Min Act: -0.0001

Data Index: 236649 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3284. Min Act: -0.0000

Data Index: 318962 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3265. Min Act: -0.0001

Data Index: 1058657 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3215. Min Act: -0.0001

Data Index: 124241 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.3164. Min Act: -0.0001

Data Index: 1088444 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2964. Min Act: -0.0001

Data Index: 483247 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2865. Min Act: -0.0001

Data Index: 516604 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2776. Min Act: -0.0001

Data Index: 92159 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2796. Min Act: -0.0001

Data Index: 929109 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1121145 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2885. Min Act: -0.0001

Data Index: 732513 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2579. Min Act: -0.0001

Data Index: 705034 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2920. Min Act: -0.0000

Data Index: 401751 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2827. Min Act: -0.0000

Data Index: 21289 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1119187 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2670. Min Act: -0.0000

Data Index: 865341 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.4008. Min Range: -0.4008

Max Act: 0.2655. Min Act: -0.0000

Data Index: 355522 (C4 (Web Text))

Max Activating Token Index: 782