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

Dataset: The Pile

Neuron 51 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1458237 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0696. Min Act: -0.0000

Data Index: 562001 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1815243 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1078164 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0011. Min Act: -0.0000

Data Index: 236521 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0168. Min Act: -0.0000

Data Index: 552863 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1413840 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9655. Min Act: -0.0000

Data Index: 345731 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9800. Min Act: -0.0000

Data Index: 833019 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1992723 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9240. Min Act: -0.0000

Data Index: 63066 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1597009 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.0696. Min Range: -1.0696

Max Act: 1.0080. Min Act: -0.0000

Data Index: 244934 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9600. Min Act: -0.0000

Data Index: 73105 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9533. Min Act: -0.0000

Data Index: 848478 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.8959. Min Act: -0.0000

Data Index: 365225 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1997426 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1450981 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.8841. Min Act: -0.0000

Data Index: 967758 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 1.0696. Min Range: -1.0696

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1009548 (The Pile)

Max Activating Token Index: 390