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

Dataset: The Pile

Neuron 1660 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1395780 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9744. Min Act: -0.0000

Data Index: 434732 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.0234. Min Range: -1.0234

Max Act: 1.0234. Min Act: -0.0000

Data Index: 644241 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9597. Min Act: -0.0000

Data Index: 445384 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9594. Min Act: -0.0000

Data Index: 912306 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 1.0234. Min Range: -1.0234

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1595391 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9342. Min Act: -0.0000

Data Index: 768802 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1625251 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9865. Min Act: -0.0000

Data Index: 386198 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8563. Min Act: -0.0000

Data Index: 911275 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1107942 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1089432 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8881. Min Act: 0.0000

Data Index: 258142 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1508341 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1665485 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.9080. Min Act: -0.0000

Data Index: 938956 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1879611 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1629978 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.8198. Min Act: -0.0000

Data Index: 225093 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 1.0234. Min Range: -1.0234

Max Act: 0.7637. Min Act: -0.0000

Data Index: 442622 (The Pile)

Max Activating Token Index: 849