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

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

Neuron 530 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0000

Data Index: 966469 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0541. Min Act: -0.0000

Data Index: 783561 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0530. Min Act: -0.0000

Data Index: 773784 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1191568 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0517. Min Act: -0.0000

Data Index: 512295 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1154072 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0488. Min Act: -0.0000

Data Index: 152619 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0467. Min Act: -0.0000

Data Index: 712644 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0493. Min Act: -0.0000

Data Index: 973308 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1233281 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1189887 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0477. Min Act: -0.0000

Data Index: 139540 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1225191 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0460. Min Act: -0.0000

Data Index: 630735 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0491. Min Act: -0.0000

Data Index: 280483 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1216644 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0432. Min Act: -0.0000

Data Index: 957893 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1111094 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0440. Min Act: -0.0000

Data Index: 320268 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0487. Min Act: -0.0000

Data Index: 702525 (C4 (Web Text))

Max Activating Token Index: 257