Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1811. Min Act: -0.0000

Data Index: 864969 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 933723 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1795. Min Act: -0.0000

Data Index: 196622 (The Pile)

Max Activating Token Index: 98

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1718. Min Act: -0.0000

Data Index: 986643 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1720695 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1348852 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1624. Min Act: -0.0000

Data Index: 203072 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1378. Min Act: -0.0000

Data Index: 826765 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1463. Min Act: -0.0000

Data Index: 106139 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1344309 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1752535 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1744893 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1430. Min Act: -0.0000

Data Index: 655608 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1743799 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1602373 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1393. Min Act: -0.0000

Data Index: 882187 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1355. Min Act: -0.0000

Data Index: 783943 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1652313 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1826219 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1160. Min Act: -0.0000

Data Index: 864883 (The Pile)

Max Activating Token Index: 90