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

Dataset: The Pile

Neuron 892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.5896. Min Act: -0.0000

Data Index: 777909 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1392849 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2046. Min Act: -0.0000

Data Index: 965004 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1934478 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.1083. Min Act: -0.0000

Data Index: 84840 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1673093 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1612804 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0685. Min Act: -0.0000

Data Index: 45409 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9975. Min Act: -0.0000

Data Index: 571717 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9633. Min Act: -0.0000

Data Index: 957727 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 1.5896. Min Range: -1.5896

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1171335 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8835. Min Act: -0.0000

Data Index: 154317 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9666. Min Act: -0.0000

Data Index: 80877 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8659. Min Act: -0.0000

Data Index: 821027 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9353. Min Act: -0.0000

Data Index: 943590 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9472. Min Act: -0.0000

Data Index: 652198 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1110082 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1573753 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1402946 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.5896. Min Range: -1.5896

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1385082 (The Pile)

Max Activating Token Index: 445