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

Dataset: The Pile

Neuron 645 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: 1.3648. Min Range: -1.3648

Max Act: 1.3320. Min Act: -0.0000

Data Index: 1508585 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.2800. Min Act: -0.0000

Data Index: 1716284 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1398935 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1199767 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1745665 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.3648. Min Act: -0.0000

Data Index: 1731709 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.1508. Min Act: -0.0000

Data Index: 262262 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.1582. Min Act: -0.0000

Data Index: 25872 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.1262. Min Act: -0.0000

Data Index: 244390 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1915346 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1194885 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0353. Min Act: -0.0000

Data Index: 865826 (The Pile)

Max Activating Token Index: 327

Text #12

Max Range: 1.3648. Min Range: -1.3648

Max Act: 0.9790. Min Act: -0.0000

Data Index: 48838 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0668. Min Act: -0.0000

Data Index: 745301 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0664. Min Act: -0.0000

Data Index: 46546 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1336310 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1488502 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0376. Min Act: -0.0000

Data Index: 935711 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1200340 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 1.3648. Min Range: -1.3648

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1878917 (The Pile)

Max Activating Token Index: 675