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

Dataset: The Pile

Neuron 1592 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: 1.8585. Min Range: -1.8585

Max Act: 1.8585. Min Act: -0.0000

Data Index: 1114503 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7776. Min Act: -0.0000

Data Index: 324445 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.5857. Min Act: -0.0000

Data Index: 784936 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.5769. Min Act: -0.0000

Data Index: 353490 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7426. Min Act: -0.0000

Data Index: 948280 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.7313. Min Act: -0.0000

Data Index: 361029 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1562556 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1789852 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6534. Min Act: -0.0000

Data Index: 650233 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6463. Min Act: -0.0000

Data Index: 830668 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1082871 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1212815 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.4828. Min Act: -0.0000

Data Index: 336152 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.5492. Min Act: -0.0000

Data Index: 276978 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1678832 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1909097 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1535618 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.3615. Min Act: -0.0000

Data Index: 1297190 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.3518. Min Act: -0.0000

Data Index: 936661 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 1.8585. Min Range: -1.8585

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1474783 (The Pile)

Max Activating Token Index: 415