Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0611. Min Act: -0.0002

Data Index: 70582 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0002

Data Index: 800322 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0611. Min Act: -0.0003

Data Index: 259803 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0601. Min Act: -0.0002

Data Index: 89390 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0560. Min Act: -0.0003

Data Index: 828925 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0525. Min Act: -0.0002

Data Index: 297504 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0531. Min Act: -0.0003

Data Index: 418888 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0537. Min Act: -0.0002

Data Index: 643739 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0519. Min Act: -0.0003

Data Index: 976362 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1329009 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0520. Min Act: -0.0003

Data Index: 79939 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1279087 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0526. Min Act: -0.0003

Data Index: 907201 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0515. Min Act: -0.0002

Data Index: 34027 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1330992 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0512. Min Act: -0.0002

Data Index: 879774 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0497. Min Act: -0.0002

Data Index: 338777 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0503. Min Act: -0.0003

Data Index: 416515 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0516. Min Act: -0.0003

Data Index: 204035 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1127111 (C4 (Web Text))

Max Activating Token Index: 427