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

Dataset: The Pile

Neuron 4795 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: 1.4444. Min Range: -1.4444

Max Act: 1.4444. Min Act: -0.0000

Data Index: 697347 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 1.4444. Min Range: -1.4444

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1847387 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1789065 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1271805 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1413137 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7986. Min Act: 0.0000

Data Index: 1878120 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8092. Min Act: -0.0000

Data Index: 978751 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8213. Min Act: -0.0000

Data Index: 27359 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7880. Min Act: -0.0000

Data Index: 518337 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1607758 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7121. Min Act: -0.0000

Data Index: 985282 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.9393. Min Act: -0.0000

Data Index: 930711 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7206. Min Act: -0.0000

Data Index: 234587 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7773. Min Act: -0.0000

Data Index: 961436 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1757647 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.7107. Min Act: -0.0000

Data Index: 400464 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.6631. Min Act: -0.0000

Data Index: 582805 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.6349. Min Act: -0.0000

Data Index: 115368 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1455089 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 1.4444. Min Range: -1.4444

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1446023 (The Pile)

Max Activating Token Index: 546