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

Dataset: The Pile

Neuron 3299 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3701. Min Range: -5.3701

Max Act: 5.3701. Min Act: -0.0000

Data Index: 1156095 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 5.3701. Min Range: -5.3701

Max Act: 5.0743. Min Act: -0.0000

Data Index: 1288243 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.5502. Min Act: -0.0000

Data Index: 1821438 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.5365. Min Act: -0.0000

Data Index: 466683 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.8842. Min Act: -0.0000

Data Index: 1438999 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.8591. Min Act: -0.0000

Data Index: 1239940 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.6326. Min Act: -0.0000

Data Index: 254918 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.8773. Min Act: -0.0000

Data Index: 1402753 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.6442. Min Act: -0.0000

Data Index: 1039742 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.6332. Min Act: -0.0000

Data Index: 1496735 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.4082. Min Act: -0.0000

Data Index: 317277 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.7673. Min Act: -0.0000

Data Index: 1272994 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.4116. Min Act: -0.0000

Data Index: 1317122 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.2189. Min Act: -0.0000

Data Index: 1167976 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.7632. Min Act: -0.0000

Data Index: 166523 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.5287. Min Act: -0.0000

Data Index: 120736 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.3566. Min Act: -0.0000

Data Index: 854838 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.3637. Min Act: -0.0000

Data Index: 1142046 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.5166. Min Act: -0.0000

Data Index: 701509 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 5.3701. Min Range: -5.3701

Max Act: 4.3524. Min Act: -0.0000

Data Index: 1685984 (The Pile)

Max Activating Token Index: 378