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

Dataset: The Pile

Neuron 368 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.9959. Min Act: -0.0000

Data Index: 1948059 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 7.1036. Min Range: -7.1036

Max Act: 7.1036. Min Act: -0.0000

Data Index: 183234 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.7090. Min Act: -0.0000

Data Index: 1450566 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.4303. Min Act: -0.0000

Data Index: 85169 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.2865. Min Act: -0.0000

Data Index: 306725 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.5102. Min Act: -0.0000

Data Index: 1470538 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.1456. Min Act: -0.0000

Data Index: 793045 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.0631. Min Act: -0.0000

Data Index: 1402109 (The Pile)

Max Activating Token Index: 361

Text #8

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.0967. Min Act: -0.0000

Data Index: 1629821 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 7.1036. Min Range: -7.1036

Max Act: 6.1379. Min Act: -0.0000

Data Index: 183180 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.5570. Min Act: -0.0000

Data Index: 1611539 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 7.1036. Min Range: -7.1036

Max Act: 4.9494. Min Act: -0.0000

Data Index: 541643 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.5450. Min Act: -0.0000

Data Index: 1881716 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.1711. Min Act: -0.0000

Data Index: 545547 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.5190. Min Act: -0.0000

Data Index: 569789 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.4731. Min Act: -0.0000

Data Index: 663804 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.7660. Min Act: -0.0000

Data Index: 498128 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.3267. Min Act: -0.0000

Data Index: 1104143 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 7.1036. Min Range: -7.1036

Max Act: 5.4890. Min Act: -0.0000

Data Index: 1365112 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 7.1036. Min Range: -7.1036

Max Act: 4.5739. Min Act: -0.0000

Data Index: 27243 (The Pile)

Max Activating Token Index: 713