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

Dataset: The Pile

Neuron 1940 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: 0.6457. Min Range: -0.6457

Max Act: 0.6457. Min Act: -0.0000

Data Index: 1162824 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1442828 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5528. Min Act: -0.0000

Data Index: 396561 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5118. Min Act: -0.0000

Data Index: 432522 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4861. Min Act: -0.0000

Data Index: 798350 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4985. Min Act: -0.0000

Data Index: 467390 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4741. Min Act: -0.0000

Data Index: 472075 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1428243 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1166934 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5066. Min Act: -0.0000

Data Index: 842097 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4444. Min Act: -0.0000

Data Index: 756740 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1953060 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1890792 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4632. Min Act: -0.0000

Data Index: 568563 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4509. Min Act: -0.0000

Data Index: 198634 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4525. Min Act: -0.0000

Data Index: 916713 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1022265 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1348640 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4597. Min Act: -0.0000

Data Index: 635388 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1009457 (The Pile)

Max Activating Token Index: 607