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

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

Neuron 4601 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1285256 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.4522. Min Act: -0.0000

Data Index: 299078 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1188068 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3980. Min Act: -0.0000

Data Index: 956407 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3884. Min Act: -0.0000

Data Index: 620660 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3864. Min Act: -0.0000

Data Index: 997986 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3593. Min Act: -0.0000

Data Index: 588495 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3658. Min Act: -0.0000

Data Index: 202026 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3536. Min Act: -0.0000

Data Index: 173776 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1083451 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3652. Min Act: -0.0000

Data Index: 451144 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1314229 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1092830 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3608. Min Act: -0.0000

Data Index: 586160 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3551. Min Act: -0.0000

Data Index: 165091 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1131110 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1318783 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1116493 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3326. Min Act: -0.0000

Data Index: 887688 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.4895. Min Range: -0.4895

Max Act: 0.3518. Min Act: -0.0000

Data Index: 14623 (C4 (Web Text))

Max Activating Token Index: 364