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

Dataset: The Pile

Neuron 3361 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1794608 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1923968 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7168. Min Act: -0.0000

Data Index: 169364 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1751732 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6977. Min Act: -0.0000

Data Index: 783644 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1085468 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1721117 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6341. Min Act: -0.0000

Data Index: 797131 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6121. Min Act: -0.0000

Data Index: 829370 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1016455 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5907. Min Act: -0.0000

Data Index: 483229 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1555883 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1280091 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6789. Min Act: -0.0000

Data Index: 754741 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1041737 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6290. Min Act: -0.0000

Data Index: 614648 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6280. Min Act: -0.0000

Data Index: 278353 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6472. Min Act: -0.0000

Data Index: 940792 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5984. Min Act: -0.0000

Data Index: 6403 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1741355 (The Pile)

Max Activating Token Index: 45