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

Dataset: The Pile

Neuron 1051 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1793306 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4915. Min Act: -0.0000

Data Index: 553537 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1186207 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1270537 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1187806 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4289. Min Act: -0.0000

Data Index: 55557 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4207. Min Act: -0.0000

Data Index: 299266 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1149855 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1671796 (The Pile)

Max Activating Token Index: 830

Text #9

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4172. Min Act: -0.0000

Data Index: 101566 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4530. Min Act: -0.0000

Data Index: 818425 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4094. Min Act: -0.0000

Data Index: 126705 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4217. Min Act: -0.0000

Data Index: 538228 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4196. Min Act: -0.0000

Data Index: 106668 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.3972. Min Act: -0.0000

Data Index: 14701 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1871815 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4130. Min Act: -0.0000

Data Index: 768957 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4086. Min Act: -0.0000

Data Index: 324049 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4077. Min Act: -0.0000

Data Index: 310360 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4242. Min Act: -0.0000

Data Index: 82366 (The Pile)

Max Activating Token Index: 483