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

Dataset: The Pile

Neuron 2148 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0465. Min Range: -5.0465

Max Act: 5.0465. Min Act: -0.0000

Data Index: 1398470 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7910. Min Act: -0.0000

Data Index: 674104 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.6440. Min Act: -0.0000

Data Index: 1994179 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.4092. Min Act: -0.0000

Data Index: 97001 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.6527. Min Act: -0.0000

Data Index: 765278 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.6388. Min Act: -0.0000

Data Index: 1174949 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.5807. Min Act: -0.0000

Data Index: 564717 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.8497. Min Act: -0.0000

Data Index: 307912 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.0754. Min Act: -0.0000

Data Index: 92014 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.2445. Min Act: -0.0000

Data Index: 1464095 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.6857. Min Act: -0.0000

Data Index: 609582 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.1204. Min Act: -0.0000

Data Index: 578027 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.7583. Min Act: -0.0000

Data Index: 1631646 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.7529. Min Act: -0.0000

Data Index: 186676 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.0850. Min Act: -0.0000

Data Index: 286628 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.8562. Min Act: -0.0000

Data Index: 1683824 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.6842. Min Act: -0.0000

Data Index: 699834 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.5709. Min Act: -0.0000

Data Index: 1297352 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.0156. Min Act: -0.0000

Data Index: 1750991 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 5.0465. Min Range: -5.0465

Max Act: 3.8149. Min Act: -0.0000

Data Index: 1399711 (The Pile)

Max Activating Token Index: 453