Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3595 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1167551 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0637. Min Act: -0.0001

Data Index: 533081 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0585. Min Act: -0.0001

Data Index: 333168 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0580. Min Act: -0.0002

Data Index: 983626 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0570. Min Act: -0.0001

Data Index: 213138 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1341456 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0558. Min Act: -0.0001

Data Index: 170339 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0526. Min Act: -0.0001

Data Index: 80530 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1023123 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0478. Min Act: -0.0001

Data Index: 63134 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0497. Min Act: -0.0001

Data Index: 362811 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1152873 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1543607 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0450. Min Act: -0.0001

Data Index: 660003 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0458. Min Act: -0.0001

Data Index: 451676 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1061431 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1478446 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0417. Min Act: -0.0001

Data Index: 149760 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0413. Min Act: -0.0001

Data Index: 273126 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0409. Min Act: -0.0001

Data Index: 650270 (C4 (Web Text))

Max Activating Token Index: 97