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

Dataset: The Pile

Neuron 674 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: 1.9649. Min Range: -1.9649

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1125577 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.9513. Min Act: -0.0000

Data Index: 1468814 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.7802. Min Act: -0.0000

Data Index: 268947 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.8375. Min Act: -0.0000

Data Index: 260796 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.9639. Min Act: -0.0000

Data Index: 321781 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1196248 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1083399 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.7827. Min Act: -0.0000

Data Index: 310333 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.7692. Min Act: -0.0000

Data Index: 363146 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.5984. Min Act: -0.0000

Data Index: 824607 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.7781. Min Act: -0.0000

Data Index: 185849 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6735. Min Act: -0.0000

Data Index: 160304 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6503. Min Act: -0.0000

Data Index: 1332453 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1009665 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1358309 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1248428 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.5530. Min Act: -0.0000

Data Index: 59204 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.6414. Min Act: -0.0000

Data Index: 683597 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1137955 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 1.9649. Min Range: -1.9649

Max Act: 1.7279. Min Act: -0.0000

Data Index: 1141322 (The Pile)

Max Activating Token Index: 427