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

Dataset: The Pile

Neuron 3125 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: 3.3344. Min Range: -3.3344

Max Act: 3.3344. Min Act: -0.0000

Data Index: 847497 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.1579. Min Act: -0.0000

Data Index: 832923 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.3270. Min Act: -0.0000

Data Index: 529108 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.0690. Min Act: -0.0000

Data Index: 1691729 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.9202. Min Act: -0.0000

Data Index: 1763862 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.0578. Min Act: -0.0000

Data Index: 1886470 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.0072. Min Act: -0.0000

Data Index: 764414 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.1314. Min Act: -0.0000

Data Index: 1506977 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.8665. Min Act: -0.0000

Data Index: 549617 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.2082. Min Act: -0.0000

Data Index: 326057 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.3027. Min Act: -0.0000

Data Index: 160972 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.0894. Min Act: -0.0000

Data Index: 85235 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.8881. Min Act: -0.0000

Data Index: 938719 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.8942. Min Act: -0.0000

Data Index: 1811114 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.8937. Min Act: -0.0000

Data Index: 750509 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.8713. Min Act: -0.0000

Data Index: 186818 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.7213. Min Act: -0.0000

Data Index: 1914216 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 3.3344. Min Range: -3.3344

Max Act: 3.0089. Min Act: -0.0000

Data Index: 1087151 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.8602. Min Act: -0.0000

Data Index: 562778 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 3.3344. Min Range: -3.3344

Max Act: 2.7014. Min Act: -0.0000

Data Index: 1681956 (The Pile)

Max Activating Token Index: 12