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

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

Neuron 649 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0003

Data Index: 538490 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0505. Min Act: -0.0003

Data Index: 595247 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0498. Min Act: -0.0003

Data Index: 864472 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0449. Min Act: -0.0003

Data Index: 691908 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1193646 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1001947 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1003838 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1318863 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0436. Min Act: -0.0003

Data Index: 916740 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0437. Min Act: -0.0003

Data Index: 486215 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0407. Min Act: -0.0003

Data Index: 999321 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1325100 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0405. Min Act: -0.0003

Data Index: 286854 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0407. Min Act: -0.0003

Data Index: 575703 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0401. Min Act: -0.0003

Data Index: 249267 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0408. Min Act: -0.0003

Data Index: 627484 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1623455 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1541759 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0389. Min Act: -0.0003

Data Index: 906162 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1077030 (C4 (Web Text))

Max Activating Token Index: 23