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

Dataset: The Pile

Neuron 3588 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: 0.8782. Min Range: -0.8782

Max Act: 0.8782. Min Act: -0.0000

Data Index: 954726 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1935785 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1793909 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6456. Min Act: -0.0000

Data Index: 897578 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1530206 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5511. Min Act: -0.0000

Data Index: 584334 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1095192 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5094. Min Act: -0.0000

Data Index: 357068 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1069819 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1174697 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1173970 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5997. Min Act: -0.0000

Data Index: 935607 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1396915 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5783. Min Act: -0.0000

Data Index: 206070 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6172. Min Act: -0.0000

Data Index: 703575 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1464037 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1664707 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1091921 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1247671 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 0.8782. Min Range: -0.8782

Max Act: 0.5805. Min Act: -0.0000

Data Index: 244782 (The Pile)

Max Activating Token Index: 11