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

Dataset: The Pile

Neuron 2914 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: 0.8503. Min Range: -0.8503

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1907303 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8449. Min Act: -0.0000

Data Index: 16758 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1872192 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7574. Min Act: -0.0000

Data Index: 454910 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1926098 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1090866 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1096233 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1689427 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7666. Min Act: -0.0000

Data Index: 503025 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7050. Min Act: -0.0000

Data Index: 575445 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6393. Min Act: -0.0000

Data Index: 680321 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7193. Min Act: -0.0000

Data Index: 758739 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1479246 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6922. Min Act: -0.0000

Data Index: 178141 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1168702 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1466238 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7371. Min Act: -0.0000

Data Index: 274807 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.7061. Min Act: -0.0000

Data Index: 911579 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1988947 (The Pile)

Max Activating Token Index: 174

Text #19

Max Range: 0.8503. Min Range: -0.8503

Max Act: 0.5918. Min Act: -0.0000

Data Index: 43581 (The Pile)

Max Activating Token Index: 726