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

Dataset: The Pile

Neuron 2881 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: 1.0378. Min Range: -1.0378

Max Act: 1.0378. Min Act: -0.0000

Data Index: 423102 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1695368 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8995. Min Act: -0.0000

Data Index: 456884 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1983481 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1075937 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1951997 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8382. Min Act: -0.0000

Data Index: 452624 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1290856 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1759181 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1400874 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8180. Min Act: -0.0000

Data Index: 373460 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1560424 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7988. Min Act: -0.0000

Data Index: 749710 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7921. Min Act: -0.0000

Data Index: 229360 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7921. Min Act: -0.0000

Data Index: 797089 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1613691 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1751737 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8113. Min Act: -0.0000

Data Index: 366549 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7823. Min Act: -0.0000

Data Index: 614723 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1550890 (The Pile)

Max Activating Token Index: 446