Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3038 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0748. Min Act: -0.0003

Data Index: 688431 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0764. Min Act: -0.0003

Data Index: 504998 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0003

Data Index: 975727 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0754. Min Act: -0.0003

Data Index: 973418 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0724. Min Act: -0.0003

Data Index: 30004 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1056489 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1289512 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0754. Min Act: -0.0003

Data Index: 930582 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0690. Min Act: -0.0003

Data Index: 292795 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0716. Min Act: -0.0003

Data Index: 785669 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0673. Min Act: -0.0003

Data Index: 505777 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0659. Min Act: -0.0003

Data Index: 769615 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1065589 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0645. Min Act: -0.0003

Data Index: 785960 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0696. Min Act: -0.0003

Data Index: 1173303 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1286755 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1260679 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1182513 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1246789 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0645. Min Act: -0.0003

Data Index: 270192 (C4 (Web Text))

Max Activating Token Index: 761