Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 206 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1855911 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2117. Min Act: -0.0000

Data Index: 449930 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1930928 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1813. Min Act: -0.0000

Data Index: 612152 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1119358 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1551184 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1712997 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1626239 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1621661 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1260947 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1560. Min Act: -0.0000

Data Index: 832473 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1978402 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1479. Min Act: -0.0000

Data Index: 714423 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1512. Min Act: -0.0000

Data Index: 368152 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1477195 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1450953 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1727938 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1544. Min Act: -0.0000

Data Index: 829878 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1020111 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1425. Min Act: -0.0000

Data Index: 605659 (The Pile)

Max Activating Token Index: 134