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

Dataset: The Pile

Neuron 3695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1054393 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2151. Min Act: -0.0000

Data Index: 987872 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1605656 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1919. Min Act: -0.0000

Data Index: 219643 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1899. Min Act: -0.0000

Data Index: 680579 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1479066 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1775. Min Act: -0.0000

Data Index: 377043 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1753. Min Act: -0.0000

Data Index: 854165 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1568687 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1723. Min Act: -0.0000

Data Index: 224290 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1842. Min Act: -0.0000

Data Index: 875590 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1729. Min Act: -0.0000

Data Index: 73386 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1874763 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1319853 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1253684 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1523102 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1231835 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1466. Min Act: -0.0000

Data Index: 698729 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1832977 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1332589 (The Pile)

Max Activating Token Index: 389