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

Dataset: The Pile

Neuron 680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.8194. Min Act: -0.0000

Data Index: 492497 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1615176 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.5141. Min Act: -0.0000

Data Index: 95093 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1499852 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.9393. Min Act: -0.0000

Data Index: 214082 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1508417 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.8194. Min Range: -1.8194

Max Act: 1.1711. Min Act: -0.0000

Data Index: 938262 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1548365 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1884279 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8457. Min Act: -0.0000

Data Index: 891502 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8963. Min Act: -0.0000

Data Index: 622584 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1474322 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1521985 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1858068 (The Pile)

Max Activating Token Index: 192

Text #14

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1156183 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8083. Min Act: -0.0000

Data Index: 98800 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1955259 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1740140 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1505943 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 1.8194. Min Range: -1.8194

Max Act: 0.7922. Min Act: -0.0000

Data Index: 403859 (The Pile)

Max Activating Token Index: 361