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

Dataset: The Pile

Neuron 344 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.1674. Min Act: -0.0000

Data Index: 310374 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 1.1674. Min Range: -1.1674

Max Act: 1.1182. Min Act: -0.0000

Data Index: 401033 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.9537. Min Act: -0.0000

Data Index: 217566 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1440005 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8505. Min Act: -0.0000

Data Index: 45296 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1618984 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8144. Min Act: -0.0000

Data Index: 439436 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1332785 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7874. Min Act: -0.0000

Data Index: 52422 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1489394 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7691. Min Act: -0.0000

Data Index: 334511 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1589154 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1115372 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1902497 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7590. Min Act: -0.0000

Data Index: 469797 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1830986 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1928180 (The Pile)

Max Activating Token Index: 623

Text #17

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7712. Min Act: -0.0000

Data Index: 706615 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7005. Min Act: -0.0000

Data Index: 725427 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1010618 (The Pile)

Max Activating Token Index: 1019