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

Dataset: The Pile

Neuron 442 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4237. Min Act: -0.0000

Data Index: 608147 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1711112 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3029. Min Act: -0.0000

Data Index: 431879 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1836144 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2018. Min Act: -0.0000

Data Index: 419080 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1333168 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0153. Min Act: -0.0000

Data Index: 324850 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0254. Min Act: -0.0000

Data Index: 604106 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1990303 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0589. Min Act: -0.0000

Data Index: 168950 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0184. Min Act: -0.0000

Data Index: 732430 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0077. Min Act: -0.0000

Data Index: 245138 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0247. Min Act: -0.0000

Data Index: 725282 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1006969 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.9141. Min Act: -0.0000

Data Index: 737054 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.9738. Min Act: -0.0000

Data Index: 1632058 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.9485. Min Act: -0.0000

Data Index: 362423 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1671637 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1655873 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 1.4782. Min Range: -1.4782

Max Act: 0.8986. Min Act: -0.0000

Data Index: 677387 (The Pile)

Max Activating Token Index: 280