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

Dataset: The Pile

Neuron 4723 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7777. Min Range: -7.7777

Max Act: 7.7777. Min Act: -0.0000

Data Index: 772139 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 7.7777. Min Range: -7.7777

Max Act: 6.3043. Min Act: -0.0000

Data Index: 820490 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 7.7777. Min Range: -7.7777

Max Act: 6.1025. Min Act: -0.0000

Data Index: 74656 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 7.7777. Min Range: -7.7777

Max Act: 6.6052. Min Act: -0.0000

Data Index: 191789 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 7.7777. Min Range: -7.7777

Max Act: 6.1226. Min Act: -0.0000

Data Index: 1307146 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.8599. Min Act: -0.0000

Data Index: 1678008 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.8406. Min Act: -0.0000

Data Index: 1095916 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.8718. Min Act: -0.0000

Data Index: 883459 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.8075. Min Act: -0.0000

Data Index: 552130 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 7.7777. Min Range: -7.7777

Max Act: 6.2878. Min Act: -0.0000

Data Index: 1250378 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.7736. Min Act: -0.0000

Data Index: 447851 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.7658. Min Act: -0.0000

Data Index: 1602842 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.4059. Min Act: -0.0000

Data Index: 133388 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.3285. Min Act: -0.0000

Data Index: 1035549 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.9457. Min Act: -0.0000

Data Index: 147843 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.5141. Min Act: -0.0000

Data Index: 85738 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 7.7777. Min Range: -7.7777

Max Act: 5.4437. Min Act: -0.0000

Data Index: 586376 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 7.7777. Min Range: -7.7777

Max Act: 4.8413. Min Act: -0.0000

Data Index: 466830 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 7.7777. Min Range: -7.7777

Max Act: 4.9834. Min Act: -0.0000

Data Index: 1526109 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 7.7777. Min Range: -7.7777

Max Act: 4.7342. Min Act: -0.0000

Data Index: 171232 (The Pile)

Max Activating Token Index: 9