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

Dataset: The Pile

Neuron 2701 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: 1.1523. Min Range: -1.1523

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1082276 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.1523. Min Range: -1.1523

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1512225 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 1.1523. Min Range: -1.1523

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1103082 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.1523. Min Range: -1.1523

Max Act: 1.1523. Min Act: -0.0000

Data Index: 1668644 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1889449 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9898. Min Act: -0.0000

Data Index: 163565 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.8970. Min Act: -0.0000

Data Index: 515364 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9161. Min Act: -0.0000

Data Index: 557757 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.8655. Min Act: -0.0000

Data Index: 837820 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1506322 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1344575 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1378087 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.1523. Min Range: -1.1523

Max Act: 1.0318. Min Act: -0.0000

Data Index: 923580 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1537332 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9257. Min Act: -0.0000

Data Index: 665957 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1252762 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1633399 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1158313 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.8834. Min Act: -0.0000

Data Index: 41434 (The Pile)

Max Activating Token Index: 830

Text #19

Max Range: 1.1523. Min Range: -1.1523

Max Act: 0.8737. Min Act: -0.0000

Data Index: 426904 (The Pile)

Max Activating Token Index: 278