Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1382 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6743. Min Act: 0.0000

Data Index: 783817 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1124765 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6533. Min Act: -0.0000

Data Index: 537246 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6404. Min Act: -0.0000

Data Index: 443522 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6370. Min Act: -0.0000

Data Index: 265995 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6541. Min Act: 0.0000

Data Index: 990957 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5952. Min Act: -0.0000

Data Index: 613522 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1131876 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6256. Min Act: -0.0000

Data Index: 519453 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5838. Min Act: -0.0000

Data Index: 467408 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5705. Min Act: 0.0000

Data Index: 855949 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5707. Min Act: 0.0000

Data Index: 1141743 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5702. Min Act: 0.0002

Data Index: 1227771 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1294182 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5680. Min Act: -0.0000

Data Index: 716935 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1891813 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1266968 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5434. Min Act: 0.0001

Data Index: 199130 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1309239 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5328. Min Act: 0.0000

Data Index: 1431867 (The Pile)

Max Activating Token Index: 737