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

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

Neuron 2290 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0002

Data Index: 373920 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0628. Min Act: -0.0002

Data Index: 41201 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1036135 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0503. Min Act: -0.0002

Data Index: 81061 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0586. Min Act: -0.0002

Data Index: 171933 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0510. Min Act: -0.0002

Data Index: 874501 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0468. Min Act: -0.0002

Data Index: 414465 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0437. Min Act: -0.0002

Data Index: 31721 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1375842 (Python Code)

Max Activating Token Index: 365

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0504. Min Act: -0.0002

Data Index: 456116 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1079988 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0500. Min Act: -0.0002

Data Index: 623967 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0481. Min Act: -0.0002

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1531171 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1157284 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0525. Min Act: -0.0002

Data Index: 883894 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1080373 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0493. Min Act: -0.0002

Data Index: 690419 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1234870 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0474. Min Act: -0.0002

Data Index: 287719 (C4 (Web Text))

Max Activating Token Index: 192