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

Dataset: The Pile

Neuron 3221 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: 1.5682. Min Range: -1.5682

Max Act: 1.5682. Min Act: -0.0000

Data Index: 655951 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1586174 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2186. Min Act: -0.0000

Data Index: 479131 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2744. Min Act: -0.0000

Data Index: 167866 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2953. Min Act: -0.0000

Data Index: 1672176 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1500319 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2345. Min Act: -0.0000

Data Index: 15192 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1368961 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1011168 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1783. Min Act: -0.0000

Data Index: 41778 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1780. Min Act: -0.0000

Data Index: 614771 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1612. Min Act: -0.0000

Data Index: 778825 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1976. Min Act: -0.0000

Data Index: 1569550 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1808. Min Act: -0.0000

Data Index: 274877 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2612. Min Act: -0.0000

Data Index: 1498432 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1350166 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0290. Min Act: -0.0000

Data Index: 147805 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1469843 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2304. Min Act: -0.0000

Data Index: 329699 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1509. Min Act: -0.0000

Data Index: 358430 (The Pile)

Max Activating Token Index: 287