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

Dataset: The Pile

Neuron 3714 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: 1.7270. Min Range: -1.7270

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1930733 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1228115 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1771417 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1551981 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.2849. Min Act: -0.0000

Data Index: 487860 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1847284 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1826. Min Act: -0.0000

Data Index: 703102 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0780. Min Act: -0.0000

Data Index: 892476 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1049604 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1477210 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1024. Min Act: -0.0000

Data Index: 454750 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1268441 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1094466 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0504. Min Act: -0.0000

Data Index: 439053 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1735689 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1131680 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1482672 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1565944 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.8476. Min Act: -0.0000

Data Index: 807941 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1631424 (The Pile)

Max Activating Token Index: 16