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

Dataset: The Pile

Neuron 4797 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.4630. Min Act: -0.0000

Data Index: 612416 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1391191 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1705031 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0384. Min Act: -0.0000

Data Index: 543629 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0008. Min Act: -0.0000

Data Index: 166090 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.9939. Min Act: -0.0000

Data Index: 813614 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.9260. Min Act: -0.0000

Data Index: 431284 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1626865 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8330. Min Act: -0.0000

Data Index: 755856 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.7498. Min Act: -0.0000

Data Index: 114924 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1719361 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8156. Min Act: -0.0000

Data Index: 512218 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8110. Min Act: -0.0000

Data Index: 540588 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8662. Min Act: -0.0000

Data Index: 588967 (The Pile)

Max Activating Token Index: 779

Text #14

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1832361 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.8724. Min Act: -0.0000

Data Index: 268206 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1401005 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1661444 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.7887. Min Act: -0.0000

Data Index: 946140 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 1.4630. Min Range: -1.4630

Max Act: 0.7849. Min Act: -0.0000

Data Index: 271068 (The Pile)

Max Activating Token Index: 278