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

Dataset: The Pile

Neuron 2171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.3707. Min Act: -0.0000

Data Index: 984649 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2097. Min Act: -0.0000

Data Index: 796554 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.2119. Min Act: -0.0000

Data Index: 846960 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.1981. Min Act: -0.0000

Data Index: 424100 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 3.3707. Min Range: -3.3707

Max Act: 3.0561. Min Act: -0.0000

Data Index: 368872 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.9132. Min Act: -0.0000

Data Index: 206315 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.8205. Min Act: -0.0000

Data Index: 1716861 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.9752. Min Act: -0.0000

Data Index: 797158 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.9581. Min Act: -0.0000

Data Index: 605380 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.6268. Min Act: -0.0000

Data Index: 552561 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1189278 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.6121. Min Act: -0.0000

Data Index: 1263366 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.5802. Min Act: -0.0000

Data Index: 1861637 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.6928. Min Act: -0.0000

Data Index: 1800241 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.7223. Min Act: -0.0000

Data Index: 466540 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.6939. Min Act: -0.0000

Data Index: 220791 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.8329. Min Act: -0.0000

Data Index: 321240 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.6480. Min Act: -0.0000

Data Index: 1791762 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.6119. Min Act: -0.0000

Data Index: 446037 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 3.3707. Min Range: -3.3707

Max Act: 2.7051. Min Act: -0.0000

Data Index: 238180 (The Pile)

Max Activating Token Index: 24