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

Dataset: The Pile

Neuron 501 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: 0.7900. Min Range: -0.7900

Max Act: 0.7900. Min Act: -0.0000

Data Index: 833207 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6454. Min Act: -0.0000

Data Index: 902372 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5718. Min Act: -0.0000

Data Index: 389772 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6072. Min Act: -0.0000

Data Index: 968401 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1161941 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1335248 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5948. Min Act: -0.0000

Data Index: 862914 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5240. Min Act: -0.0001

Data Index: 1105042 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1096618 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5725. Min Act: -0.0000

Data Index: 550007 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5362. Min Act: -0.0000

Data Index: 655827 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1004126 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1160515 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1573053 (The Pile)

Max Activating Token Index: 248

Text #14

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5064. Min Act: -0.0000

Data Index: 753578 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1448327 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1542572 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1077763 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1125543 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1078585 (The Pile)

Max Activating Token Index: 593