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

Dataset: The Pile

Neuron 341 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.4373. Min Act: -0.0000

Data Index: 197687 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.4454. Min Act: -0.0000

Data Index: 113632 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.4064. Min Act: -0.0000

Data Index: 1929943 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2145. Min Act: -0.0000

Data Index: 657553 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1017619 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1106680 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1643324 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1358723 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1899774 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1261573 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1393. Min Act: -0.0000

Data Index: 472018 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.1083. Min Act: -0.0000

Data Index: 354745 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1094621 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1703625 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0514. Min Act: -0.0000

Data Index: 979364 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0568. Min Act: -0.0000

Data Index: 687680 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1855989 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0441. Min Act: -0.0000

Data Index: 794690 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 1.4454. Min Range: -1.4454

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1218643 (The Pile)

Max Activating Token Index: 419

Text #19

Max Range: 1.4454. Min Range: -1.4454

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1702002 (The Pile)

Max Activating Token Index: 464