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

Dataset: The Pile

Neuron 1025 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5462. Min Act: -0.0000

Data Index: 477213 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5381. Min Act: -0.0000

Data Index: 106440 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1680133 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4452. Min Act: -0.0000

Data Index: 83582 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4401. Min Act: -0.0000

Data Index: 605109 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1067379 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4472. Min Act: -0.0000

Data Index: 335200 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1738688 (The Pile)

Max Activating Token Index: 514

Text #8

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1472327 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3853. Min Act: -0.0000

Data Index: 1581495 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1635249 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3823. Min Act: -0.0000

Data Index: 849602 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4384. Min Act: -0.0000

Data Index: 116300 (The Pile)

Max Activating Token Index: 1017

Text #13

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1892013 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1590566 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1648540 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3864. Min Act: -0.0000

Data Index: 222472 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3840. Min Act: -0.0000

Data Index: 707706 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3844. Min Act: -0.0000

Data Index: 452199 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3470. Min Act: -0.0000

Data Index: 296102 (The Pile)

Max Activating Token Index: 616