Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1668 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0546. Min Act: -0.0002

Data Index: 642951 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0567. Min Act: -0.0002

Data Index: 220433 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0002

Data Index: 238113 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1247671 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1201305 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1153749 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1359845 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0538. Min Act: -0.0002

Data Index: 549035 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1261560 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0537. Min Act: -0.0002

Data Index: 210139 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0559. Min Act: -0.0002

Data Index: 138526 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0567. Min Act: -0.0002

Data Index: 881679 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1162238 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0529. Min Act: -0.0002

Data Index: 21100 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0528. Min Act: -0.0002

Data Index: 99029 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0537. Min Act: -0.0002

Data Index: 118236 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0537. Min Act: -0.0002

Data Index: 862272 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0537. Min Act: -0.0002

Data Index: 143651 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0541. Min Act: -0.0002

Data Index: 18363 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0503. Min Act: -0.0002

Data Index: 505397 (C4 (Web Text))

Max Activating Token Index: 458