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

Dataset: The Pile

Neuron 4274 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.6003. Min Act: -0.0000

Data Index: 879161 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1848843 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1140246 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1711012 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.5120. Min Act: -0.0000

Data Index: 193764 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1231845 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1945824 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4784. Min Act: -0.0000

Data Index: 733604 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1023829 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4558. Min Act: -0.0000

Data Index: 461785 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1829403 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4361. Min Act: -0.0000

Data Index: 860884 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4331. Min Act: -0.0000

Data Index: 788474 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1694786 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1708597 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4279. Min Act: -0.0000

Data Index: 390517 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4452. Min Act: -0.0000

Data Index: 276468 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4266. Min Act: -0.0000

Data Index: 720771 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4394. Min Act: -0.0000

Data Index: 411987 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.6003. Min Range: -0.6003

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1959511 (The Pile)

Max Activating Token Index: 218