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

Dataset: The Pile

Neuron 2047 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1369768 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2169. Min Act: -0.0000

Data Index: 919730 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1654728 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2011. Min Act: -0.0000

Data Index: 408288 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1928. Min Act: -0.0000

Data Index: 234540 (The Pile)

Max Activating Token Index: 536

Text #5

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1364954 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1955. Min Act: -0.0000

Data Index: 188781 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1927159 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1626. Min Act: -0.0000

Data Index: 16808 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1162684 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1384533 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1126863 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1236623 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1420. Min Act: -0.0000

Data Index: 115567 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1464. Min Act: -0.0000

Data Index: 798605 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1427. Min Act: -0.0000

Data Index: 698603 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1379. Min Act: -0.0000

Data Index: 825457 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1272496 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1348. Min Act: -0.0000

Data Index: 956753 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1985318 (The Pile)

Max Activating Token Index: 565