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

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

Neuron 1730 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0002

Data Index: 540343 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0599. Min Act: -0.0002

Data Index: 611363 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0593. Min Act: -0.0002

Data Index: 731803 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0590. Min Act: -0.0002

Data Index: 114886 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0566. Min Act: -0.0002

Data Index: 321830 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1199300 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1437834 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1310593 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1175688 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1147441 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0540. Min Act: -0.0002

Data Index: 636419 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0533. Min Act: -0.0001

Data Index: 290026 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0538. Min Act: -0.0002

Data Index: 707327 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0564. Min Act: -0.0001

Data Index: 370774 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0513. Min Act: -0.0002

Data Index: 25198 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0553. Min Act: -0.0001

Data Index: 952003 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1452091 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1353177 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1305232 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0512. Min Act: -0.0001

Data Index: 85401 (C4 (Web Text))

Max Activating Token Index: 362