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

Dataset: The Pile

Neuron 3344 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: 0.6804. Min Range: -0.6804

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1959707 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1545502 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1642617 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1906472 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5375. Min Act: -0.0000

Data Index: 600108 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5364. Min Act: -0.0000

Data Index: 383486 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5812. Min Act: -0.0000

Data Index: 294508 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1191102 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1198878 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1604704 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1534436 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5638. Min Act: -0.0000

Data Index: 282269 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5479. Min Act: -0.0000

Data Index: 738915 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5751. Min Act: -0.0000

Data Index: 299261 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1486206 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5482. Min Act: -0.0000

Data Index: 938214 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1795421 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5167. Min Act: -0.0000

Data Index: 741626 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1149958 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.6804. Min Range: -0.6804

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1030694 (The Pile)

Max Activating Token Index: 922