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

Dataset: The Pile

Neuron 28 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: 0.8005. Min Range: -0.8005

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1098032 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1399113 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1746460 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1805731 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1086. Min Act: -0.0000

Data Index: 963342 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.2106. Min Act: -0.0000

Data Index: 243604 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.2563. Min Act: -0.0000

Data Index: 968554 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.2115. Min Act: -0.0000

Data Index: 525357 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1374. Min Act: -0.0000

Data Index: 193954 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1816. Min Act: -0.0000

Data Index: 997692 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1964327 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1036226 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1912365 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1056474 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1788. Min Act: -0.0000

Data Index: 48318 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1738. Min Act: -0.0000

Data Index: 2580 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1929022 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1670. Min Act: -0.0000

Data Index: 797177 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1505665 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.8005. Min Range: -0.8005

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1551048 (The Pile)

Max Activating Token Index: 686