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

Dataset: The Pile

Neuron 8 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.7137. Min Act: -0.0000

Data Index: 659103 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1182641 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6333. Min Act: -0.0000

Data Index: 801637 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6456. Min Act: -0.0000

Data Index: 673118 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1068587 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1775372 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5981. Min Act: -0.0000

Data Index: 547191 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5575. Min Act: -0.0000

Data Index: 383307 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5554. Min Act: -0.0000

Data Index: 543258 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1970999 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5772. Min Act: -0.0000

Data Index: 863523 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1532797 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1245231 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5618. Min Act: -0.0000

Data Index: 193024 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1187874 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1496617 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5627. Min Act: -0.0000

Data Index: 888612 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1695499 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1870718 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5360. Min Act: -0.0000

Data Index: 794929 (The Pile)

Max Activating Token Index: 141