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

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

Neuron 285 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: 0.5082. Min Range: -0.5082

Max Act: 0.4998. Min Act: -0.0000

Data Index: 716422 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.5006. Min Act: -0.0000

Data Index: 638608 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4880. Min Act: -0.0000

Data Index: 212085 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1595722 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4516. Min Act: -0.0000

Data Index: 562986 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4004. Min Act: -0.0000

Data Index: 220294 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4585. Min Act: -0.0000

Data Index: 222622 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.5082. Min Act: -0.0000

Data Index: 359498 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4093. Min Act: -0.0000

Data Index: 704602 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3882. Min Act: -0.0000

Data Index: 625507 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3834. Min Act: -0.0000

Data Index: 177201 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1460827 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3800. Min Act: -0.0000

Data Index: 57340 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4113. Min Act: -0.0000

Data Index: 847095 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3586. Min Act: -0.0000

Data Index: 800328 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1370831 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3754. Min Act: -0.0000

Data Index: 137016 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1201494 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3659. Min Act: -0.0000

Data Index: 830753 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3832. Min Act: -0.0000

Data Index: 370838 (C4 (Web Text))

Max Activating Token Index: 173