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

Dataset: The Pile

Neuron 2570 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: 7.1579. Min Range: -7.1579

Max Act: 7.1579. Min Act: -0.0000

Data Index: 1890907 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 7.1579. Min Range: -7.1579

Max Act: 7.0743. Min Act: -0.0000

Data Index: 678749 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.6969. Min Act: -0.0000

Data Index: 580653 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.9980. Min Act: -0.0000

Data Index: 1914656 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.9239. Min Act: -0.0000

Data Index: 1541941 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.6383. Min Act: -0.0000

Data Index: 1474928 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.6119. Min Act: -0.0000

Data Index: 892168 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.9338. Min Act: -0.0000

Data Index: 1011974 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.7680. Min Act: -0.0000

Data Index: 166128 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.6835. Min Act: -0.0000

Data Index: 464710 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.4759. Min Act: -0.0000

Data Index: 62415 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.6064. Min Act: -0.0000

Data Index: 607228 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.9788. Min Act: -0.0000

Data Index: 456207 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.3974. Min Act: -0.0000

Data Index: 1306376 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.8004. Min Act: -0.0000

Data Index: 1080798 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.4113. Min Act: -0.0000

Data Index: 242603 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.5698. Min Act: -0.0000

Data Index: 1068821 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.5106. Min Act: -0.0000

Data Index: 866797 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.5191. Min Act: -0.0000

Data Index: 1673822 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 7.1579. Min Range: -7.1579

Max Act: 6.2769. Min Act: -0.0000

Data Index: 547762 (The Pile)

Max Activating Token Index: 617