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

Dataset: The Pile

Neuron 4348 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: 1.7092. Min Range: -1.7092

Max Act: 1.7092. Min Act: -0.0000

Data Index: 1029967 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.5425. Min Act: -0.0000

Data Index: 1694723 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.5293. Min Act: -0.0000

Data Index: 113807 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.2452. Min Act: -0.0000

Data Index: 568340 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1205028 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.2247. Min Act: -0.0000

Data Index: 297613 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1803. Min Act: -0.0000

Data Index: 655976 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.2060. Min Act: -0.0000

Data Index: 963702 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0592. Min Act: -0.0000

Data Index: 537516 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1715. Min Act: 0.0000

Data Index: 727577 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1676. Min Act: -0.0000

Data Index: 252261 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.2226. Min Act: 0.0000

Data Index: 1384543 (The Pile)

Max Activating Token Index: 343

Text #12

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1432488 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0906. Min Act: -0.0000

Data Index: 873588 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1715987 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1040. Min Act: -0.0000

Data Index: 720426 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1402413 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.1473. Min Act: 0.0000

Data Index: 536329 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1768547 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.7092. Min Range: -1.7092

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1637651 (The Pile)

Max Activating Token Index: 29