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

Dataset: The Pile

Neuron 859 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: 3.1338. Min Range: -3.1338

Max Act: 3.1338. Min Act: -0.0000

Data Index: 1396851 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.6230. Min Act: -0.0000

Data Index: 1755276 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.8150. Min Act: -0.0000

Data Index: 1478760 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.5029. Min Act: -0.0000

Data Index: 1105030 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.3283. Min Act: -0.0000

Data Index: 457733 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1811. Min Act: -0.0000

Data Index: 627408 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1367. Min Act: -0.0000

Data Index: 674943 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.2461. Min Act: -0.0000

Data Index: 404491 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1342. Min Act: -0.0000

Data Index: 1900635 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1809. Min Act: -0.0000

Data Index: 861420 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.4260. Min Act: -0.0000

Data Index: 1169792 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1884991 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 3.1338. Min Range: -3.1338

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1604187 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.2678. Min Act: -0.0000

Data Index: 726537 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1276. Min Act: -0.0000

Data Index: 713931 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.1253. Min Act: -0.0000

Data Index: 34756 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.0054. Min Act: -0.0000

Data Index: 1231711 (The Pile)

Max Activating Token Index: 774

Text #17

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.0888. Min Act: -0.0000

Data Index: 1357502 (The Pile)

Max Activating Token Index: 609

Text #18

Max Range: 3.1338. Min Range: -3.1338

Max Act: 1.8574. Min Act: -0.0000

Data Index: 776560 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 3.1338. Min Range: -3.1338

Max Act: 2.0429. Min Act: -0.0000

Data Index: 1320146 (The Pile)

Max Activating Token Index: 907