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

Dataset: The Pile

Neuron 4941 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: 3.9520. Min Range: -3.9520

Max Act: 3.9520. Min Act: -0.0000

Data Index: 460478 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.7331. Min Act: -0.0000

Data Index: 1834028 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.7851. Min Act: -0.0000

Data Index: 1377662 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.7989. Min Act: -0.0000

Data Index: 427811 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.4398. Min Act: -0.0000

Data Index: 1919747 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.9407. Min Act: -0.0000

Data Index: 146401 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.5859. Min Act: -0.0000

Data Index: 489561 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.5355. Min Act: -0.0000

Data Index: 1196523 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.5267. Min Act: -0.0000

Data Index: 1565890 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.6816. Min Act: -0.0000

Data Index: 1538559 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.5129. Min Act: -0.0000

Data Index: 299911 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.5063. Min Act: -0.0000

Data Index: 1191741 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.6480. Min Act: -0.0000

Data Index: 1715628 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.4904. Min Act: -0.0000

Data Index: 1401218 (The Pile)

Max Activating Token Index: 516

Text #14

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.6392. Min Act: -0.0000

Data Index: 511671 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.6606. Min Act: -0.0000

Data Index: 1711805 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.3457. Min Act: -0.0000

Data Index: 1753745 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.5016. Min Act: -0.0000

Data Index: 269911 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.4612. Min Act: -0.0000

Data Index: 1316718 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 3.9520. Min Range: -3.9520

Max Act: 3.4684. Min Act: -0.0000

Data Index: 433868 (The Pile)

Max Activating Token Index: 503