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

Dataset: The Pile

Neuron 2741 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.7907. Min Range: -10.7907

Max Act: 10.7907. Min Act: -0.0000

Data Index: 1454911 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 10.7907. Min Range: -10.7907

Max Act: 10.3882. Min Act: -0.0000

Data Index: 417517 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 10.7907. Min Range: -10.7907

Max Act: 9.8759. Min Act: -0.0000

Data Index: 1967678 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 10.7907. Min Range: -10.7907

Max Act: 9.3188. Min Act: -0.0000

Data Index: 1567247 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 10.7907. Min Range: -10.7907

Max Act: 8.6956. Min Act: -0.0000

Data Index: 385705 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.7037. Min Act: -0.0000

Data Index: 347719 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.5828. Min Act: -0.0000

Data Index: 1658279 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.8473. Min Act: -0.0000

Data Index: 494523 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 10.7907. Min Range: -10.7907

Max Act: 8.0159. Min Act: -0.0000

Data Index: 1984056 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.4116. Min Act: -0.0000

Data Index: 1391883 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.5649. Min Act: -0.0000

Data Index: 719688 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.7025. Min Act: -0.0000

Data Index: 367962 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.2880. Min Act: -0.0000

Data Index: 768924 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 10.7907. Min Range: -10.7907

Max Act: 5.8679. Min Act: -0.0000

Data Index: 1256023 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 10.7907. Min Range: -10.7907

Max Act: 4.7957. Min Act: -0.0000

Data Index: 767413 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 10.7907. Min Range: -10.7907

Max Act: 7.1149. Min Act: -0.0000

Data Index: 1480105 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 10.7907. Min Range: -10.7907

Max Act: 6.3888. Min Act: -0.0000

Data Index: 1429319 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 10.7907. Min Range: -10.7907

Max Act: 6.3336. Min Act: -0.0000

Data Index: 1712930 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 10.7907. Min Range: -10.7907

Max Act: 6.8732. Min Act: -0.0000

Data Index: 1537466 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 10.7907. Min Range: -10.7907

Max Act: 6.4356. Min Act: -0.0000

Data Index: 1114369 (The Pile)

Max Activating Token Index: 820