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

Dataset: The Pile

Neuron 452 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: 1.4197. Min Range: -1.4197

Max Act: 1.4197. Min Act: -0.0000

Data Index: 593561 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1362831 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.2684. Min Act: -0.0000

Data Index: 170168 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1829. Min Act: -0.0000

Data Index: 267339 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1852828 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.2555. Min Act: -0.0000

Data Index: 330522 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1169097 (The Pile)

Max Activating Token Index: 61

Text #7

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1210. Min Act: -0.0000

Data Index: 508403 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1232. Min Act: -0.0000

Data Index: 587475 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1063173 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.1014. Min Act: -0.0000

Data Index: 1384964 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0758. Min Act: -0.0000

Data Index: 211603 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1709159 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1050184 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1260161 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 1.4197. Min Range: -1.4197

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1640216 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1911730 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0213. Min Act: -0.0000

Data Index: 969915 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0157. Min Act: -0.0000

Data Index: 473666 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.4197. Min Range: -1.4197

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1378591 (The Pile)

Max Activating Token Index: 490