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

Dataset: The Pile

Neuron 4569 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6218. Min Act: -0.0000

Data Index: 820205 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6520. Min Act: -0.0000

Data Index: 260880 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1917135 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1310749 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1702997 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1504443 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1992050 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1985840 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1855702 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1106888 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1005906 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5732. Min Act: -0.0000

Data Index: 620691 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5309. Min Act: -0.0000

Data Index: 664796 (The Pile)

Max Activating Token Index: 774

Text #13

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1268746 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5525. Min Act: -0.0000

Data Index: 644918 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1732493 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1804217 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5314. Min Act: -0.0000

Data Index: 265173 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1757000 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1535717 (The Pile)

Max Activating Token Index: 979