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

Dataset: The Pile

Neuron 1821 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0994. Min Act: -0.0000

Data Index: 349453 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1073862 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0761. Min Act: -0.0000

Data Index: 733866 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0637. Min Act: -0.0000

Data Index: 856120 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0626. Min Act: -0.0000

Data Index: 131114 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1400837 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1141072 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0600. Min Act: -0.0000

Data Index: 628152 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1908076 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1311062 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1840600 (The Pile)

Max Activating Token Index: 537

Text #11

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1446309 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1732233 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0496. Min Act: -0.0000

Data Index: 512042 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0501. Min Act: -0.0000

Data Index: 358922 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0518. Min Act: -0.0000

Data Index: 994964 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1782249 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0533. Min Act: -0.0000

Data Index: 417715 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0495. Min Act: -0.0000

Data Index: 156902 (The Pile)

Max Activating Token Index: 865

Text #19

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0513. Min Act: -0.0000

Data Index: 998443 (The Pile)

Max Activating Token Index: 615