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

Dataset: The Pile

Neuron 4954 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: 1.0862. Min Range: -1.0862

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1971652 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8465. Min Act: -0.0000

Data Index: 1763096 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9098. Min Act: -0.0000

Data Index: 956747 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0688. Min Act: -0.0000

Data Index: 211898 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.4855. Min Act: -0.0000

Data Index: 341614 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8303. Min Act: -0.0000

Data Index: 438293 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6375. Min Act: -0.0000

Data Index: 364383 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7849. Min Act: -0.0000

Data Index: 869037 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1149930 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1328261 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1046568 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1746256 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5905. Min Act: -0.0000

Data Index: 806330 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1713381 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5199. Min Act: -0.0000

Data Index: 257510 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1226181 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1246662 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6495. Min Act: -0.0000

Data Index: 725856 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.6645. Min Act: -0.0000

Data Index: 633968 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.3477. Min Act: -0.0000

Data Index: 429539 (The Pile)

Max Activating Token Index: 852