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

Dataset: The Pile

Neuron 151 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: 0.8839. Min Range: -0.8839

Max Act: 0.8839. Min Act: -0.0000

Data Index: 484379 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8278. Min Act: -0.0000

Data Index: 954421 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1399886 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8666. Min Act: -0.0000

Data Index: 64608 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1172431 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8582. Min Act: -0.0000

Data Index: 75119 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7999. Min Act: -0.0000

Data Index: 517036 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1010399 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8403. Min Act: -0.0000

Data Index: 572018 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1852816 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7845. Min Act: -0.0000

Data Index: 427887 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7558. Min Act: -0.0000

Data Index: 31461 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8005. Min Act: -0.0000

Data Index: 982360 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1249567 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8238. Min Act: -0.0000

Data Index: 562486 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1479921 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7927. Min Act: -0.0000

Data Index: 568431 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1409031 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7383. Min Act: -0.0000

Data Index: 847054 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7533. Min Act: -0.0000

Data Index: 202282 (The Pile)

Max Activating Token Index: 866