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

Dataset: The Pile

Neuron 2090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1687723 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8659. Min Act: -0.0000

Data Index: 969465 (The Pile)

Max Activating Token Index: 589

Text #2

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1983380 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1057954 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7965. Min Act: -0.0000

Data Index: 461676 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1284107 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7942. Min Act: 0.0000

Data Index: 352830 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8078. Min Act: -0.0000

Data Index: 390512 (The Pile)

Max Activating Token Index: 317

Text #8

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1746581 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7757. Min Act: 0.0000

Data Index: 510975 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7472. Min Act: -0.0000

Data Index: 541319 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1631348 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1252753 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7189. Min Act: -0.0000

Data Index: 669243 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1786373 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.8403. Min Act: -0.0000

Data Index: 958552 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1885780 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1852173 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1616881 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.8992. Min Range: -0.8992

Max Act: 0.7189. Min Act: -0.0000

Data Index: 129805 (The Pile)

Max Activating Token Index: 147