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

Dataset: The Pile

Neuron 1529 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.3349. Min Act: -0.0000

Data Index: 811863 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2620. Min Act: -0.0000

Data Index: 735840 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2577. Min Act: -0.0000

Data Index: 649342 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1238838 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1143522 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2634. Min Act: -0.0000

Data Index: 874897 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2349. Min Act: -0.0000

Data Index: 653719 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2377. Min Act: -0.0000

Data Index: 470011 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1539523 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1365159 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2141. Min Act: -0.0000

Data Index: 96189 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1969899 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1532215 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1629784 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.2224. Min Act: -0.0000

Data Index: 41498 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1153502 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1514510 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1793044 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1978. Min Act: -0.0000

Data Index: 805842 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.3349. Min Range: -0.3349

Max Act: 0.1984. Min Act: -0.0000

Data Index: 507853 (The Pile)

Max Activating Token Index: 727