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

Dataset: The Pile

Neuron 2574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8907. Min Act: -0.0000

Data Index: 725453 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8800. Min Act: -0.0000

Data Index: 123384 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8662. Min Act: -0.0000

Data Index: 923674 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7677. Min Act: -0.0000

Data Index: 694049 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1072043 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7618. Min Act: -0.0000

Data Index: 158050 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7159. Min Act: -0.0000

Data Index: 912953 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1571928 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6582. Min Act: -0.0000

Data Index: 603327 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1339229 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1959647 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1459128 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1679115 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1466100 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6727. Min Act: -0.0000

Data Index: 639216 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6572. Min Act: -0.0000

Data Index: 452936 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6465. Min Act: -0.0000

Data Index: 7642 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1056002 (The Pile)

Max Activating Token Index: 509

Text #18

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6539. Min Act: -0.0000

Data Index: 770235 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6088. Min Act: -0.0000

Data Index: 316059 (The Pile)

Max Activating Token Index: 195