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

Dataset: The Pile

Neuron 3918 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: 1.1764. Min Range: -1.1764

Max Act: 1.1764. Min Act: -0.0000

Data Index: 495331 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9736. Min Act: -0.0001

Data Index: 341733 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0657. Min Act: -0.0000

Data Index: 73298 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0816. Min Act: -0.0001

Data Index: 76009 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0322. Min Act: -0.0000

Data Index: 341378 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1667228 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9066. Min Act: -0.0000

Data Index: 90926 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0794. Min Act: -0.0001

Data Index: 1968227 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1697733 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9463. Min Act: -0.0000

Data Index: 727233 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1365888 (The Pile)

Max Activating Token Index: 337

Text #11

Max Range: 1.1764. Min Range: -1.1764

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1252771 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1733522 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9296. Min Act: -0.0000

Data Index: 585443 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1606595 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.8970. Min Act: -0.0001

Data Index: 1473389 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.8802. Min Act: -0.0000

Data Index: 729113 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.9376. Min Act: -0.0000

Data Index: 316950 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1435677 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 1.1764. Min Range: -1.1764

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1690479 (The Pile)

Max Activating Token Index: 901