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

Dataset: The Pile

Neuron 2054 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: 0.8506. Min Range: -0.8506

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1945060 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1614747 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1421462 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1299113 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6851. Min Act: -0.0000

Data Index: 747908 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6382. Min Act: -0.0000

Data Index: 921908 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1427399 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6465. Min Act: -0.0000

Data Index: 89447 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1828636 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1485553 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1925726 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1617916 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6280. Min Act: -0.0000

Data Index: 696615 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6023. Min Act: -0.0000

Data Index: 975111 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5770. Min Act: -0.0000

Data Index: 384338 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5559. Min Act: -0.0000

Data Index: 564799 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1025773 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1835279 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1019830 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1781356 (The Pile)

Max Activating Token Index: 59