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

Dataset: The Pile

Neuron 2462 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1870270 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1431153 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3637. Min Act: -0.0000

Data Index: 377056 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3358. Min Act: -0.0000

Data Index: 684369 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3308. Min Act: -0.0000

Data Index: 184965 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3219. Min Act: -0.0000

Data Index: 62437 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1619834 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1701813 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2973. Min Act: 0.0000

Data Index: 160524 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2848. Min Act: -0.0000

Data Index: 782106 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1379248 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2933. Min Act: -0.0000

Data Index: 94228 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3032. Min Act: -0.0000

Data Index: 36230 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1824764 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2823. Min Act: -0.0000

Data Index: 529100 (The Pile)

Max Activating Token Index: 300

Text #15

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2802. Min Act: -0.0000

Data Index: 418102 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1611434 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1555472 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1638000 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2769. Min Act: -0.0000

Data Index: 116353 (The Pile)

Max Activating Token Index: 415