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

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

Neuron 2195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0537. Min Act: -0.0003

Data Index: 777749 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1606380 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1203615 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0470. Min Act: -0.0003

Data Index: 920167 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0505. Min Act: -0.0003

Data Index: 555368 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0558. Min Act: -0.0003

Data Index: 102690 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0450. Min Act: -0.0003

Data Index: 584771 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0446. Min Act: -0.0003

Data Index: 154599 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0502. Min Act: -0.0003

Data Index: 607514 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0433. Min Act: -0.0003

Data Index: 403923 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0511. Min Act: -0.0003

Data Index: 1330588 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0003

Data Index: 987065 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1250491 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1519329 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1551929 (Python Code)

Max Activating Token Index: 842

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1456840 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1365684 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1365905 (Python Code)

Max Activating Token Index: 622

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0456. Min Act: -0.0003

Data Index: 902430 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0463. Min Act: -0.0003

Data Index: 342672 (C4 (Web Text))

Max Activating Token Index: 305