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

Dataset: The Pile

Neuron 1254 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1440. Min Act: -0.0000

Data Index: 716554 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.2038. Min Act: -0.0000

Data Index: 58858 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1576. Min Act: -0.0000

Data Index: 523302 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1292716 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0732. Min Act: -0.0000

Data Index: 230265 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1530. Min Act: -0.0000

Data Index: 860208 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1951022 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1608239 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1624520 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0881. Min Act: -0.0000

Data Index: 231166 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1920376 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1368. Min Act: -0.0000

Data Index: 985421 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1344891 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1545594 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.1285. Min Act: -0.0000

Data Index: 468193 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1946135 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0056. Min Act: -0.0000

Data Index: 339713 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0863. Min Act: -0.0000

Data Index: 806808 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 1.2038. Min Range: -1.2038

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1115968 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 1.2038. Min Range: -1.2038

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1811561 (The Pile)

Max Activating Token Index: 692