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

Dataset: The Pile

Neuron 2518 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: 3.5535. Min Range: -3.5535

Max Act: 3.5535. Min Act: -0.0000

Data Index: 389434 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.4052. Min Act: -0.0000

Data Index: 1771934 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.2863. Min Act: -0.0000

Data Index: 1019692 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.0437. Min Act: -0.0000

Data Index: 442626 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.9732. Min Act: -0.0000

Data Index: 1478966 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.7841. Min Act: -0.0000

Data Index: 1024047 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.5443. Min Act: -0.0000

Data Index: 359466 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.1141. Min Act: -0.0000

Data Index: 1807819 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.6591. Min Act: -0.0000

Data Index: 1913972 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 3.5535. Min Range: -3.5535

Max Act: 3.0191. Min Act: -0.0000

Data Index: 142461 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.3610. Min Act: -0.0000

Data Index: 1347959 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.7409. Min Act: -0.0000

Data Index: 1462186 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1715877 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.1692. Min Act: -0.0000

Data Index: 612911 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.5226. Min Act: -0.0000

Data Index: 160690 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.1671. Min Act: -0.0000

Data Index: 25223 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.4094. Min Act: -0.0000

Data Index: 1031525 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.2650. Min Act: -0.0000

Data Index: 165666 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.1437. Min Act: -0.0000

Data Index: 1591929 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 3.5535. Min Range: -3.5535

Max Act: 2.3771. Min Act: -0.0000

Data Index: 1764674 (The Pile)

Max Activating Token Index: 583