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

Dataset: The Pile

Neuron 1806 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: 5.5469. Min Range: -5.5469

Max Act: 5.5469. Min Act: -0.0000

Data Index: 332925 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.4472. Min Act: -0.0000

Data Index: 285140 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.3689. Min Act: -0.0000

Data Index: 1275834 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.2693. Min Act: -0.0000

Data Index: 680485 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.1034. Min Act: -0.0000

Data Index: 1343427 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.0396. Min Act: -0.0000

Data Index: 1344752 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.2378. Min Act: -0.0000

Data Index: 1670161 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.2255. Min Act: -0.0000

Data Index: 1294912 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.1227. Min Act: -0.0000

Data Index: 1335218 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.3304. Min Act: -0.0000

Data Index: 1759737 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.1065. Min Act: -0.0000

Data Index: 1773708 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.1087. Min Act: -0.0000

Data Index: 26391 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.7098. Min Act: -0.0000

Data Index: 1691751 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.9048. Min Act: -0.0000

Data Index: 1844017 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.7682. Min Act: -0.0000

Data Index: 1302549 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 5.5469. Min Range: -5.5469

Max Act: 5.0977. Min Act: -0.0000

Data Index: 1641167 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.7653. Min Act: -0.0000

Data Index: 655736 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.9086. Min Act: -0.0000

Data Index: 1326483 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.8705. Min Act: -0.0000

Data Index: 335698 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 5.5469. Min Range: -5.5469

Max Act: 4.7396. Min Act: -0.0000

Data Index: 1453097 (The Pile)

Max Activating Token Index: 13