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

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

Neuron 3536 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.4396. Min Act: -0.0000

Data Index: 458626 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3757. Min Act: -0.0000

Data Index: 563848 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3904. Min Act: -0.0000

Data Index: 340313 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3770. Min Act: 0.0000

Data Index: 142363 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1102753 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3759. Min Act: -0.0000

Data Index: 491589 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1026402 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3548. Min Act: -0.0000

Data Index: 43508 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3382. Min Act: -0.0000

Data Index: 768679 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3204. Min Act: -0.0000

Data Index: 174729 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3338. Min Act: -0.0000

Data Index: 536808 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3249. Min Act: -0.0000

Data Index: 899530 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2912. Min Act: -0.0000

Data Index: 699446 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1267742 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3180. Min Act: -0.0000

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3012. Min Act: -0.0000

Data Index: 724795 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1070095 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2654. Min Act: -0.0000

Data Index: 868141 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.3120. Min Act: -0.0000

Data Index: 666442 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.4396. Min Range: -0.4396

Max Act: 0.2880. Min Act: -0.0000

Data Index: 706796 (C4 (Web Text))

Max Activating Token Index: 709