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

Dataset: The Pile

Neuron 3088 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: 3.2679. Min Range: -3.2679

Max Act: 3.2122. Min Act: -0.0000

Data Index: 165514 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.9378. Min Act: -0.0000

Data Index: 669939 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 3.2679. Min Range: -3.2679

Max Act: 3.1091. Min Act: -0.0000

Data Index: 882401 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 3.2679. Min Range: -3.2679

Max Act: 3.2472. Min Act: -0.0000

Data Index: 1789758 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 3.2679. Min Range: -3.2679

Max Act: 3.2679. Min Act: -0.0000

Data Index: 1511276 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.6683. Min Act: -0.0000

Data Index: 868561 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.9181. Min Act: -0.0000

Data Index: 1995024 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.9867. Min Act: -0.0000

Data Index: 665860 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.7180. Min Act: -0.0000

Data Index: 929741 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.8441. Min Act: -0.0000

Data Index: 198426 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.9496. Min Act: -0.0000

Data Index: 1021032 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.9385. Min Act: -0.0000

Data Index: 1203280 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.9557. Min Act: -0.0000

Data Index: 1806352 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.6578. Min Act: -0.0000

Data Index: 1746658 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1535010 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.6564. Min Act: -0.0000

Data Index: 829385 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 3.2679. Min Range: -3.2679

Max Act: 3.2326. Min Act: -0.0000

Data Index: 535188 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 3.2679. Min Range: -3.2679

Max Act: 3.1654. Min Act: -0.0000

Data Index: 193849 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.3950. Min Act: -0.0000

Data Index: 295847 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 3.2679. Min Range: -3.2679

Max Act: 2.6554. Min Act: -0.0000

Data Index: 1602453 (The Pile)

Max Activating Token Index: 967