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

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

Neuron 1438 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0003

Data Index: 68734 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0613. Min Act: -0.0003

Data Index: 703270 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1168102 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1117609 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0546. Min Act: -0.0003

Data Index: 290183 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0573. Min Act: -0.0003

Data Index: 210971 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0539. Min Act: -0.0003

Data Index: 475307 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0558. Min Act: -0.0003

Data Index: 373022 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1352429 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0536. Min Act: -0.0003

Data Index: 941141 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1102511 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0516. Min Act: -0.0003

Data Index: 938091 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0527. Min Act: -0.0003

Data Index: 361003 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0500. Min Act: -0.0003

Data Index: 920808 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0516. Min Act: -0.0003

Data Index: 903410 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0498. Min Act: -0.0003

Data Index: 405494 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0534. Min Act: -0.0003

Data Index: 828178 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0513. Min Act: -0.0003

Data Index: 965507 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1113936 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0509. Min Act: -0.0003

Data Index: 210284 (C4 (Web Text))

Max Activating Token Index: 329