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

Dataset: The Pile

Neuron 2832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.7650. Min Act: -0.0000

Data Index: 475241 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6596. Min Act: -0.0000

Data Index: 730817 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6260. Min Act: -0.0000

Data Index: 373967 (The Pile)

Max Activating Token Index: 873

Text #3

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6307. Min Act: -0.0000

Data Index: 878063 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6043. Min Act: -0.0000

Data Index: 341665 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1745121 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5591. Min Act: 0.0000

Data Index: 1012524 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5987. Min Act: -0.0000

Data Index: 438404 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5717. Min Act: -0.0000

Data Index: 792259 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1443905 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5210. Min Act: -0.0000

Data Index: 741999 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5878. Min Act: -0.0000

Data Index: 417506 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1807096 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1182168 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5913. Min Act: -0.0000

Data Index: 714972 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.6125. Min Act: -0.0000

Data Index: 300283 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1211568 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5910. Min Act: -0.0000

Data Index: 890430 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1287757 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.7650. Min Range: -0.7650

Max Act: 0.5401. Min Act: -0.0000

Data Index: 365836 (The Pile)

Max Activating Token Index: 913