Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4115 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4871. Min Act: -0.0000

Data Index: 433673 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4663. Min Act: -0.0000

Data Index: 151067 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3695. Min Act: -0.0000

Data Index: 612143 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1075366 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3760. Min Act: -0.0000

Data Index: 689820 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3707. Min Act: -0.0000

Data Index: 384972 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3563. Min Act: -0.0000

Data Index: 683671 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3672. Min Act: -0.0000

Data Index: 389308 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1357268 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3709. Min Act: -0.0000

Data Index: 51283 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1108242 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1127278 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3329. Min Act: -0.0000

Data Index: 918511 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1114207 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1301190 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1354420 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1212240 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3341. Min Act: -0.0000

Data Index: 883122 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3579. Min Act: -0.0000

Data Index: 429116 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1152381 (C4 (Web Text))

Max Activating Token Index: 796