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

Dataset: The Pile

Neuron 4746 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: 3.5088. Min Range: -3.5088

Max Act: 3.5088. Min Act: -0.0000

Data Index: 1033754 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.1402. Min Act: -0.0000

Data Index: 1647388 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.2182. Min Act: -0.0000

Data Index: 227054 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.2870. Min Act: -0.0000

Data Index: 1268618 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.8900. Min Act: -0.0000

Data Index: 1999950 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.0722. Min Act: -0.0000

Data Index: 596152 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.0583. Min Act: -0.0000

Data Index: 744267 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.4281. Min Act: -0.0000

Data Index: 1342912 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.6097. Min Act: -0.0000

Data Index: 1219525 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.9199. Min Act: -0.0000

Data Index: 111052 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.6961. Min Act: -0.0000

Data Index: 1542070 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 3.5088. Min Range: -3.5088

Max Act: 3.0722. Min Act: -0.0000

Data Index: 1528243 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.7958. Min Act: -0.0000

Data Index: 596505 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.7996. Min Act: -0.0000

Data Index: 1267057 (The Pile)

Max Activating Token Index: 294

Text #14

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.3373. Min Act: -0.0000

Data Index: 902385 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.3862. Min Act: -0.0000

Data Index: 184750 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.5784. Min Act: -0.0000

Data Index: 20144 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.5641. Min Act: -0.0000

Data Index: 562532 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.3094. Min Act: -0.0000

Data Index: 672100 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 3.5088. Min Range: -3.5088

Max Act: 2.1680. Min Act: -0.0000

Data Index: 1421658 (The Pile)

Max Activating Token Index: 530