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

Dataset: The Pile

Neuron 1193 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1000335 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1832211 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.9002. Min Act: -0.0000

Data Index: 480058 (The Pile)

Max Activating Token Index: 171

Text #3

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1610289 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8088. Min Act: -0.0000

Data Index: 213997 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1291675 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1305073 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1566136 (The Pile)

Max Activating Token Index: 35

Text #8

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7750. Min Act: -0.0000

Data Index: 886394 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7704. Min Act: -0.0000

Data Index: 396410 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7489. Min Act: -0.0000

Data Index: 792375 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7648. Min Act: -0.0000

Data Index: 156673 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6865. Min Act: -0.0000

Data Index: 701933 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7268. Min Act: -0.0000

Data Index: 192566 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1369700 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1034 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1517292 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6841. Min Act: -0.0000

Data Index: 651111 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1537585 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.9002. Min Range: -0.9002

Max Act: 0.7444. Min Act: -0.0000

Data Index: 994860 (The Pile)

Max Activating Token Index: 727