Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.3181. Min Act: -0.0000

Data Index: 501733 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.5608. Min Act: -0.0000

Data Index: 588944 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1271393 (The Pile)

Max Activating Token Index: 221

Text #3

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1631. Min Act: -0.0000

Data Index: 392197 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2490. Min Act: -0.0000

Data Index: 220869 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2355. Min Act: -0.0000

Data Index: 474440 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2379. Min Act: -0.0000

Data Index: 204566 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1751. Min Act: -0.0000

Data Index: 537518 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1868500 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1879494 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1567. Min Act: -0.0000

Data Index: 652419 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1589422 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2418. Min Act: -0.0000

Data Index: 368511 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1656485 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1097487 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1984871 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1983840 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1177258 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 1.5608. Min Range: -1.5608

Max Act: 1.1482. Min Act: -0.0000

Data Index: 894091 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 1.5608. Min Range: -1.5608

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1701650 (The Pile)

Max Activating Token Index: 12