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

Dataset: The Pile

Neuron 3393 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: 5.2484. Min Range: -5.2484

Max Act: 5.2484. Min Act: -0.0000

Data Index: 1483700 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.7276. Min Act: -0.0000

Data Index: 65494 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.6276. Min Act: -0.0000

Data Index: 932819 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.3650. Min Act: -0.0000

Data Index: 616183 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.4947. Min Act: -0.0000

Data Index: 932192 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.8394. Min Act: -0.0000

Data Index: 167565 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.3945. Min Act: -0.0000

Data Index: 645989 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.0076. Min Act: -0.0000

Data Index: 159520 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.1927. Min Act: -0.0000

Data Index: 3365 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.8283. Min Act: -0.0000

Data Index: 653842 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.7881. Min Act: -0.0000

Data Index: 1074755 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.9269. Min Act: -0.0000

Data Index: 578155 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.1910. Min Act: -0.0000

Data Index: 316614 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.1775. Min Act: -0.0000

Data Index: 1385086 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.9953. Min Act: -0.0000

Data Index: 908880 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.3222. Min Act: -0.0000

Data Index: 1967373 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.9533. Min Act: -0.0000

Data Index: 246460 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.9606. Min Act: -0.0000

Data Index: 997514 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 5.2484. Min Range: -5.2484

Max Act: 3.6192. Min Act: -0.0000

Data Index: 247662 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 5.2484. Min Range: -5.2484

Max Act: 4.0808. Min Act: -0.0000

Data Index: 261417 (The Pile)

Max Activating Token Index: 216