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

Dataset: The Pile

Neuron 2531 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: 7.5694. Min Range: -7.5694

Max Act: 7.0290. Min Act: -0.0000

Data Index: 1510508 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 7.5694. Min Range: -7.5694

Max Act: 7.2398. Min Act: -0.0000

Data Index: 1589253 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 7.5694. Min Range: -7.5694

Max Act: 7.5694. Min Act: -0.0000

Data Index: 1327026 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 7.5694. Min Range: -7.5694

Max Act: 7.1073. Min Act: -0.0000

Data Index: 596505 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 7.5694. Min Range: -7.5694

Max Act: 6.7626. Min Act: -0.0000

Data Index: 430824 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 7.5694. Min Range: -7.5694

Max Act: 6.9907. Min Act: -0.0000

Data Index: 1999950 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 7.5694. Min Range: -7.5694

Max Act: 7.0763. Min Act: -0.0000

Data Index: 147081 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 7.5694. Min Range: -7.5694

Max Act: 7.0117. Min Act: -0.0000

Data Index: 1528243 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 7.5694. Min Range: -7.5694

Max Act: 6.8637. Min Act: -0.0000

Data Index: 1667489 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 7.5694. Min Range: -7.5694

Max Act: 6.1752. Min Act: -0.0000

Data Index: 12969 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.8819. Min Act: -0.0000

Data Index: 1647388 (The Pile)

Max Activating Token Index: 185

Text #11

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.7612. Min Act: -0.0000

Data Index: 1771521 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.6904. Min Act: -0.0000

Data Index: 1033754 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.5847. Min Act: -0.0000

Data Index: 309770 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.2134. Min Act: -0.0000

Data Index: 20144 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.5491. Min Act: -0.0000

Data Index: 593780 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.4497. Min Act: -0.0000

Data Index: 111052 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.3144. Min Act: -0.0000

Data Index: 758433 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.5472. Min Act: -0.0000

Data Index: 1323946 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 7.5694. Min Range: -7.5694

Max Act: 5.2963. Min Act: -0.0000

Data Index: 235656 (The Pile)

Max Activating Token Index: 383