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

Dataset: The Pile

Neuron 468 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: 0.8073. Min Range: -0.8073

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1009533 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7183. Min Act: -0.0000

Data Index: 254193 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1702725 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7115. Min Act: -0.0000

Data Index: 368158 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1457017 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6192. Min Act: -0.0000

Data Index: 696275 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1648803 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6296. Min Act: -0.0000

Data Index: 7494 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1994226 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1319745 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6988. Min Act: -0.0000

Data Index: 148328 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6044. Min Act: -0.0000

Data Index: 206882 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1621650 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5946. Min Act: -0.0000

Data Index: 548122 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1415012 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5482. Min Act: -0.0000

Data Index: 4451 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1271063 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1740646 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5710. Min Act: -0.0000

Data Index: 480401 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1004654 (The Pile)

Max Activating Token Index: 997