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

Dataset: The Pile

Neuron 280 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: 0.8496. Min Range: -0.8496

Max Act: 0.8496. Min Act: -0.0000

Data Index: 549079 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.8018. Min Act: 0.0000

Data Index: 1872216 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1604282 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7255. Min Act: -0.0000

Data Index: 347333 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7228. Min Act: 0.0000

Data Index: 1506752 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.7285. Min Act: 0.0000

Data Index: 584711 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6910. Min Act: -0.0000

Data Index: 282944 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1397305 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1586679 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6386. Min Act: 0.0000

Data Index: 243103 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1135213 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6227. Min Act: -0.0000

Data Index: 861968 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1185360 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6340. Min Act: -0.0000

Data Index: 614539 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6134. Min Act: -0.0000

Data Index: 805311 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6049. Min Act: 0.0000

Data Index: 839361 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1025742 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.5754. Min Act: -0.0000

Data Index: 820950 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6309. Min Act: -0.0000

Data Index: 454994 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.8496. Min Range: -0.8496

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1957280 (The Pile)

Max Activating Token Index: 356