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

Dataset: The Pile

Neuron 701 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1211140 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8650. Min Act: -0.0000

Data Index: 1928249 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1782170 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8501. Min Act: -0.0000

Data Index: 816550 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1081225 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6518. Min Act: -0.0000

Data Index: 1581853 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1331159 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7593. Min Act: -0.0000

Data Index: 107824 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7676. Min Act: -0.0000

Data Index: 873601 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1274165 (The Pile)

Max Activating Token Index: 249

Text #10

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7482. Min Act: -0.0000

Data Index: 522793 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7555. Min Act: -0.0000

Data Index: 984630 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8199. Min Act: -0.0000

Data Index: 145183 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1018602 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7167. Min Act: -0.0000

Data Index: 96365 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7175. Min Act: -0.0000

Data Index: 545308 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7253. Min Act: -0.0000

Data Index: 590957 (The Pile)

Max Activating Token Index: 311

Text #17

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.8045. Min Act: -0.0000

Data Index: 1600295 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.6060. Min Act: -0.0000

Data Index: 13507 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 1.8917. Min Range: -1.8917

Max Act: 1.7353. Min Act: -0.0000

Data Index: 1322667 (The Pile)

Max Activating Token Index: 672