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

Dataset: The Pile

Neuron 3314 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: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0000

Data Index: 926251 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5821. Min Act: -0.0000

Data Index: 373342 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1138622 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1502207 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1500858 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5708. Min Act: -0.0000

Data Index: 21451 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1377944 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4826. Min Act: -0.0000

Data Index: 280274 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1517176 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1967138 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5068. Min Act: -0.0000

Data Index: 454355 (The Pile)

Max Activating Token Index: 819

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4795. Min Act: -0.0000

Data Index: 741237 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4730. Min Act: -0.0000

Data Index: 533909 (The Pile)

Max Activating Token Index: 240

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4772. Min Act: -0.0000

Data Index: 167209 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4806. Min Act: -0.0000

Data Index: 726287 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1860878 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1116789 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1664643 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4545. Min Act: -0.0000

Data Index: 244031 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.4317. Min Act: -0.0000

Data Index: 401941 (The Pile)

Max Activating Token Index: 363