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

Dataset: The Pile

Neuron 4381 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: 1.3616. Min Range: -1.3616

Max Act: 1.3616. Min Act: -0.0000

Data Index: 760869 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 1.3616. Min Range: -1.3616

Max Act: 1.0749. Min Act: -0.0000

Data Index: 951797 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9292. Min Act: -0.0000

Data Index: 881700 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.9135. Min Act: -0.0000

Data Index: 682427 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1396079 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1003668 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8745. Min Act: -0.0000

Data Index: 956155 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1260445 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8601. Min Act: -0.0000

Data Index: 56316 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8227. Min Act: -0.0000

Data Index: 741158 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1909046 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8174. Min Act: -0.0000

Data Index: 18514 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7671. Min Act: -0.0000

Data Index: 53349 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7831. Min Act: -0.0000

Data Index: 245241 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1712961 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1583535 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7699. Min Act: -0.0000

Data Index: 197778 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1611724 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1882720 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.3616. Min Range: -1.3616

Max Act: 0.7393. Min Act: -0.0000

Data Index: 942602 (The Pile)

Max Activating Token Index: 651