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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5014 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1548371 (Python Code)

Max Activating Token Index: 793

Text #1

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1296183 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1562106 (Python Code)

Max Activating Token Index: 199

Text #3

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1033744 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3902. Min Act: -0.0000

Data Index: 644612 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4405. Min Act: -0.0000

Data Index: 355266 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1517625 (Python Code)

Max Activating Token Index: 610

Text #7

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1615831 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3685. Min Act: -0.0000

Data Index: 166481 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3673. Min Act: -0.0000

Data Index: 221004 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3933. Min Act: -0.0000

Data Index: 84492 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1636797 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.4290. Min Act: -0.0000

Data Index: 102633 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3791. Min Act: -0.0000

Data Index: 707679 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1183172 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1273288 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1301563 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3297. Min Act: -0.0000

Data Index: 358040 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1564493 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.5623. Min Range: -0.5623

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1274179 (C4 (Web Text))

Max Activating Token Index: 419