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

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

Neuron 1138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0000

Data Index: 632812 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1046716 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1009861 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1550430 (Python Code)

Max Activating Token Index: 519

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0446. Min Act: -0.0000

Data Index: 182321 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0405. Min Act: -0.0000

Data Index: 36920 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1403627 (Python Code)

Max Activating Token Index: 274

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1532886 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1127004 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1568927 (Python Code)

Max Activating Token Index: 522

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0355. Min Act: -0.0001

Data Index: 353527 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1536675 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1467897 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1494729 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1380712 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0405. Min Act: -0.0001

Data Index: 700503 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1096051 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0336. Min Act: -0.0000

Data Index: 1529437 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0347. Min Act: -0.0001

Data Index: 936654 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0345. Min Act: -0.0001

Data Index: 302409 (C4 (Web Text))

Max Activating Token Index: 379