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

Dataset: The Pile

Neuron 3585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0375. Min Range: -1.0375

Max Act: 1.0375. Min Act: -0.0000

Data Index: 526894 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7980. Min Act: -0.0000

Data Index: 714999 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1352604 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1638277 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7602. Min Act: -0.0000

Data Index: 866386 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1193692 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7631. Min Act: -0.0000

Data Index: 504443 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1179422 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1177013 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1354786 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1210574 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1390902 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7069. Min Act: -0.0000

Data Index: 220765 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1999284 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1940252 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1700417 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6280. Min Act: -0.0000

Data Index: 161902 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6527. Min Act: -0.0000

Data Index: 745024 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1106174 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6118. Min Act: -0.0000

Data Index: 548697 (The Pile)

Max Activating Token Index: 937