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

Dataset: The Pile

Neuron 503 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: 0.5604. Min Range: -0.5604

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1537839 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1683959 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1161431 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4712. Min Act: -0.0000

Data Index: 509834 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4353. Min Act: -0.0000

Data Index: 291519 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4442. Min Act: -0.0000

Data Index: 696923 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1243738 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1642473 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1294680 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1984917 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1201663 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1807755 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4310. Min Act: -0.0000

Data Index: 592373 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4012. Min Act: -0.0000

Data Index: 182590 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1664952 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4426. Min Act: -0.0000

Data Index: 793247 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4284. Min Act: -0.0000

Data Index: 877911 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1684291 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1059248 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.5604. Min Range: -0.5604

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1790795 (The Pile)

Max Activating Token Index: 454