Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.4343. Min Act: -0.0000

Data Index: 793815 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1031117 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3665. Min Act: -0.0001

Data Index: 118448 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1190062 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1016175 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3586. Min Act: -0.0001

Data Index: 735041 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3603. Min Act: -0.0001

Data Index: 1285645 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3545. Min Act: -0.0000

Data Index: 602674 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3493. Min Act: -0.0001

Data Index: 704638 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3594. Min Act: -0.0001

Data Index: 392595 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3557. Min Act: -0.0001

Data Index: 697507 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1235720 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3539. Min Act: -0.0001

Data Index: 51224 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3376. Min Act: -0.0000

Data Index: 976662 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3429. Min Act: -0.0001

Data Index: 48908 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3329. Min Act: -0.0000

Data Index: 16194 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3291. Min Act: -0.0001

Data Index: 1051577 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3281. Min Act: -0.0001

Data Index: 543425 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3268. Min Act: -0.0000

Data Index: 903801 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.4343. Min Range: -0.4343

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1277560 (C4 (Web Text))

Max Activating Token Index: 468