Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 534 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1660. Min Act: -0.0000

Data Index: 426873 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1596669 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1300589 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8244. Min Act: -0.0000

Data Index: 334691 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1872138 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1815220 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7930. Min Act: -0.0000

Data Index: 877664 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1386478 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1908241 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7943. Min Act: -0.0000

Data Index: 856746 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7791. Min Act: -0.0000

Data Index: 373569 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8124. Min Act: -0.0000

Data Index: 304366 (The Pile)

Max Activating Token Index: 150

Text #12

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1750792 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7971. Min Act: -0.0000

Data Index: 23004 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8328. Min Act: -0.0000

Data Index: 21759 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1027194 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7896. Min Act: -0.0000

Data Index: 858281 (The Pile)

Max Activating Token Index: 661

Text #17

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8339. Min Act: -0.0000

Data Index: 664138 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1803021 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1575545 (The Pile)

Max Activating Token Index: 751