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

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

Neuron 3482 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0001

Data Index: 839655 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1194177 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1142547 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0600. Min Act: -0.0001

Data Index: 908654 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0569. Min Act: -0.0001

Data Index: 116815 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0680. Min Act: -0.0001

Data Index: 383315 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0490. Min Act: -0.0001

Data Index: 67309 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0543. Min Act: -0.0001

Data Index: 692545 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0561. Min Act: -0.0001

Data Index: 849660 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0582. Min Act: -0.0001

Data Index: 161095 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1032160 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1293722 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0550. Min Act: -0.0001

Data Index: 124969 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0477. Min Act: -0.0001

Data Index: 723453 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0591. Min Act: -0.0001

Data Index: 791847 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0610. Min Act: -0.0001

Data Index: 224017 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0594. Min Act: -0.0001

Data Index: 880260 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0561. Min Act: -0.0001

Data Index: 338479 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0497. Min Act: -0.0001

Data Index: 318645 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0544. Min Act: -0.0001

Data Index: 339190 (C4 (Web Text))

Max Activating Token Index: 695