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

Dataset: The Pile

Neuron 1506 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: 1.9824. Min Range: -1.9824

Max Act: 1.9824. Min Act: -0.0000

Data Index: 712494 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.8228. Min Act: -0.0000

Data Index: 1789791 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5972. Min Act: -0.0000

Data Index: 502313 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7269. Min Act: -0.0000

Data Index: 1249637 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.6313. Min Act: -0.0000

Data Index: 707008 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1210598 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1100031 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1888656 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5347. Min Act: -0.0000

Data Index: 504643 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1510140 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.4221. Min Act: -0.0000

Data Index: 117683 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1356465 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1160276 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.4709. Min Act: -0.0000

Data Index: 855113 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1449984 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1876475 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.3240. Min Act: -0.0000

Data Index: 937525 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1180497 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.6090. Min Act: -0.0000

Data Index: 237643 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 1.9824. Min Range: -1.9824

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1371970 (The Pile)

Max Activating Token Index: 490