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

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

Neuron 3620 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1329637 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1085273 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0003

Data Index: 378640 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1068239 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0712. Min Act: -0.0003

Data Index: 680601 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0685. Min Act: -0.0003

Data Index: 1161320 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0663. Min Act: -0.0003

Data Index: 334355 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0634. Min Act: -0.0003

Data Index: 608018 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0639. Min Act: -0.0003

Data Index: 605999 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0610. Min Act: -0.0003

Data Index: 584487 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0678. Min Act: -0.0003

Data Index: 10154 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0728. Min Act: -0.0003

Data Index: 420405 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0678. Min Act: -0.0003

Data Index: 79233 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0730. Min Act: -0.0003

Data Index: 674570 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0726. Min Act: -0.0003

Data Index: 502164 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0687. Min Act: -0.0003

Data Index: 978994 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0681. Min Act: -0.0003

Data Index: 434296 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0702. Min Act: -0.0003

Data Index: 713191 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1165268 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0602. Min Act: -0.0003

Data Index: 755686 (C4 (Web Text))

Max Activating Token Index: 588