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

Dataset: The Pile

Neuron 3444 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1743878 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1864296 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1998231 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4791. Min Act: -0.0000

Data Index: 980983 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4963. Min Act: -0.0000

Data Index: 252917 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4828. Min Act: -0.0000

Data Index: 13506 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4732. Min Act: -0.0000

Data Index: 901881 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1064859 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1170459 (The Pile)

Max Activating Token Index: 831

Text #9

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4417. Min Act: -0.0000

Data Index: 635205 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1487120 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1882406 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1833382 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1188019 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4055. Min Act: -0.0000

Data Index: 822949 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1423557 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1045427 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3886. Min Act: -0.0000

Data Index: 167987 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1157771 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.5533. Min Range: -0.5533

Max Act: 0.3860. Min Act: -0.0001

Data Index: 1492986 (The Pile)

Max Activating Token Index: 712