Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4489 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1573224 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1376888 (Python Code)

Max Activating Token Index: 935

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1023306 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1627723 (Python Code)

Max Activating Token Index: 856

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1604795 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1566401 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1639967 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1540252 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1443239 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1511713 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1393641 (Python Code)

Max Activating Token Index: 552

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0541. Min Act: -0.0000

Data Index: 530592 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1397624 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1409833 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1586329 (Python Code)

Max Activating Token Index: 690

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1302418 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0507. Min Act: -0.0000

Data Index: 829891 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0494. Min Act: -0.0000

Data Index: 489423 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1632881 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1550417 (Python Code)

Max Activating Token Index: 854