Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2012 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0679. Min Act: -0.0004

Data Index: 473560 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0602. Min Act: -0.0004

Data Index: 1279994 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0004

Data Index: 495220 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0609. Min Act: -0.0004

Data Index: 1014246 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0554. Min Act: -0.0004

Data Index: 1093932 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0576. Min Act: -0.0004

Data Index: 857743 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0571. Min Act: -0.0004

Data Index: 184607 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0586. Min Act: -0.0004

Data Index: 36915 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0560. Min Act: -0.0004

Data Index: 502530 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0603. Min Act: -0.0004

Data Index: 297242 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0555. Min Act: -0.0004

Data Index: 860124 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0532. Min Act: -0.0004

Data Index: 1106777 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0578. Min Act: -0.0004

Data Index: 539056 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0572. Min Act: -0.0004

Data Index: 1094651 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0571. Min Act: -0.0004

Data Index: 42433 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0591. Min Act: -0.0004

Data Index: 1349296 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0544. Min Act: -0.0004

Data Index: 278320 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0542. Min Act: -0.0004

Data Index: 984581 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0542. Min Act: -0.0004

Data Index: 107391 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0538. Min Act: -0.0004

Data Index: 436164 (C4 (Web Text))

Max Activating Token Index: 807