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

Dataset: The Pile

Neuron 1481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0007. Min Range: -3.0007

Max Act: 3.0007. Min Act: -0.0000

Data Index: 484234 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.6785. Min Act: -0.0000

Data Index: 661107 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.6600. Min Act: -0.0000

Data Index: 1851883 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.3761. Min Act: -0.0000

Data Index: 652236 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.4843. Min Act: -0.0000

Data Index: 1544857 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.6160. Min Act: -0.0000

Data Index: 322862 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.6790. Min Act: -0.0000

Data Index: 1505804 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.6587. Min Act: -0.0000

Data Index: 332856 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.3978. Min Act: -0.0000

Data Index: 1291430 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.2686. Min Act: -0.0000

Data Index: 827141 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.3731. Min Act: -0.0000

Data Index: 575879 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.3600. Min Act: -0.0000

Data Index: 93911 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.4801. Min Act: -0.0000

Data Index: 1390896 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.4882. Min Act: -0.0000

Data Index: 751411 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.1120. Min Act: -0.0000

Data Index: 1808557 (The Pile)

Max Activating Token Index: 605

Text #15

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.4626. Min Act: -0.0000

Data Index: 1155248 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.4485. Min Act: -0.0000

Data Index: 1728524 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.5385. Min Act: -0.0000

Data Index: 807710 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.5156. Min Act: -0.0000

Data Index: 292105 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 3.0007. Min Range: -3.0007

Max Act: 2.1536. Min Act: -0.0000

Data Index: 1391129 (The Pile)

Max Activating Token Index: 882