Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1098245 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0846. Min Act: -0.0000

Data Index: 269643 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0763. Min Act: -0.0000

Data Index: 948998 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0773. Min Act: -0.0000

Data Index: 500382 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0797. Min Act: -0.0000

Data Index: 668547 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0741. Min Act: -0.0000

Data Index: 351925 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0693. Min Act: -0.0000

Data Index: 103995 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0678. Min Act: -0.0000

Data Index: 79880 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0726. Min Act: -0.0000

Data Index: 879818 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0686. Min Act: -0.0000

Data Index: 863995 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0683. Min Act: -0.0000

Data Index: 339142 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1355804 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0696. Min Act: -0.0000

Data Index: 231522 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0618. Min Act: -0.0000

Data Index: 240493 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0665. Min Act: -0.0000

Data Index: 25422 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1146254 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0645. Min Act: -0.0000

Data Index: 8836 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0614. Min Act: -0.0000

Data Index: 27966 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1297004 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0633. Min Act: -0.0000

Data Index: 667873 (C4 (Web Text))

Max Activating Token Index: 211