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

Dataset: The Pile

Neuron 942 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: 0.8471. Min Range: -0.8471

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1267202 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7245. Min Act: -0.0000

Data Index: 414611 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1996144 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1470181 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1235062 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6236. Min Act: -0.0000

Data Index: 131368 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1815282 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1904900 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5208. Min Act: -0.0000

Data Index: 23882 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5667. Min Act: -0.0000

Data Index: 956609 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1984458 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1999078 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1721620 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1232453 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1057273 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1231373 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1174397 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4247. Min Act: -0.0000

Data Index: 142155 (The Pile)

Max Activating Token Index: 909

Text #18

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1095777 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.4324. Min Act: -0.0000

Data Index: 132313 (The Pile)

Max Activating Token Index: 628