Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2480 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.2222. Min Act: -0.0000

Data Index: 478175 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1556314 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.1074. Min Act: -0.0000

Data Index: 204633 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0619. Min Act: -0.0000

Data Index: 765643 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0745. Min Act: -0.0000

Data Index: 972218 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1320176 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.1293. Min Act: -0.0000

Data Index: 863502 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0371. Min Act: -0.0000

Data Index: 249727 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0056. Min Act: -0.0000

Data Index: 941860 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1116979 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1997788 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9912. Min Act: -0.0000

Data Index: 626100 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1486768 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1235585 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1181762 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0282. Min Act: -0.0000

Data Index: 194398 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9368. Min Act: -0.0000

Data Index: 235653 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.0046. Min Act: -0.0000

Data Index: 520319 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1769652 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1542317 (The Pile)

Max Activating Token Index: 601