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

Dataset: The Pile

Neuron 3858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.6925. Min Act: -0.0000

Data Index: 1301459 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1755155 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1869479 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.7139. Min Act: -0.0000

Data Index: 1714317 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1751837 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3923. Min Act: -0.0000

Data Index: 263875 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3887. Min Act: -0.0000

Data Index: 1340061 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1061206 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.4397. Min Act: -0.0000

Data Index: 498125 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2581. Min Act: -0.0000

Data Index: 567086 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.3066. Min Act: -0.0000

Data Index: 526745 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2222. Min Act: -0.0000

Data Index: 575253 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2994. Min Act: -0.0000

Data Index: 815388 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2733. Min Act: -0.0000

Data Index: 297145 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2714. Min Act: -0.0000

Data Index: 927 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2404. Min Act: -0.0000

Data Index: 333198 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1679955 (The Pile)

Max Activating Token Index: 590

Text #17

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.1975. Min Act: -0.0000

Data Index: 912140 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1664077 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 1.7139. Min Range: -1.7139

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1066212 (The Pile)

Max Activating Token Index: 409