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

Dataset: The Pile

Neuron 1465 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: 0.3534. Min Range: -0.3534

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1363907 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2843. Min Act: -0.0000

Data Index: 689222 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1754450 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1934. Min Act: -0.0000

Data Index: 745154 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1406537 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1520460 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1346653 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1726. Min Act: -0.0000

Data Index: 260414 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1718. Min Act: -0.0000

Data Index: 65622 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1675651 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1194. Min Act: -0.0000

Data Index: 852690 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1550973 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1661. Min Act: -0.0000

Data Index: 461332 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1321. Min Act: -0.0000

Data Index: 650310 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1740675 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1306. Min Act: -0.0000

Data Index: 269320 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1337555 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1153259 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1519. Min Act: 0.0000

Data Index: 1739853 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.3534. Min Range: -0.3534

Max Act: 0.1623. Min Act: 0.0000

Data Index: 527942 (The Pile)

Max Activating Token Index: 711