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

Dataset: The Pile

Neuron 2717 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: 0.4059. Min Range: -0.4059

Max Act: 0.3804. Min Act: -0.0000

Data Index: 871303 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.4059. Min Act: -0.0000

Data Index: 645537 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1839480 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3660. Min Act: -0.0000

Data Index: 518537 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3872. Min Act: -0.0000

Data Index: 599498 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3852. Min Act: -0.0000

Data Index: 549825 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3552. Min Act: -0.0000

Data Index: 570054 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3548. Min Act: -0.0001

Data Index: 1406905 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3617. Min Act: -0.0000

Data Index: 678290 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1881897 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1788696 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3534. Min Act: -0.0000

Data Index: 83776 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1924928 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3255. Min Act: -0.0000

Data Index: 545276 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1164406 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1142938 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3458. Min Act: -0.0000

Data Index: 41429 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3577. Min Act: -0.0000

Data Index: 741929 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1185302 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 0.4059. Min Range: -0.4059

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1891507 (The Pile)

Max Activating Token Index: 155