Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1869 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1957. Min Act: -0.0001

Data Index: 856706 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1744. Min Act: -0.0000

Data Index: 534581 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1061725 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1608. Min Act: -0.0000

Data Index: 395222 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1285256 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1621. Min Act: -0.0001

Data Index: 210071 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1456658 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1470853 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1273939 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1501857 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1553926 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1368333 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1129418 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1549126 (Python Code)

Max Activating Token Index: 305

Text #14

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1451. Min Act: -0.0001

Data Index: 572830 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1338. Min Act: -0.0000

Data Index: 673497 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1436. Min Act: -0.0000

Data Index: 783117 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1478. Min Act: -0.0001

Data Index: 714024 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1312299 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1357. Min Act: -0.0001

Data Index: 457072 (C4 (Web Text))

Max Activating Token Index: 20