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

Dataset: The Pile

Neuron 981 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3880. Min Act: -0.0000

Data Index: 650426 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1632000 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1189804 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3246. Min Act: -0.0000

Data Index: 904782 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1873482 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1241577 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1786266 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1988299 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1249623 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1098864 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1943488 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1870940 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1234234 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2330. Min Act: -0.0000

Data Index: 620387 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2792. Min Act: -0.0000

Data Index: 221325 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2416. Min Act: -0.0000

Data Index: 336044 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1094622 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1055602 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1457891 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 0.4084. Min Range: -0.4084

Max Act: 0.2199. Min Act: -0.0000

Data Index: 342354 (The Pile)

Max Activating Token Index: 772