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

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

Neuron 1275 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1837. Min Act: -0.0000

Data Index: 851741 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1976. Min Act: -0.0001

Data Index: 1451718 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1733. Min Act: -0.0001

Data Index: 624525 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1432910 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1238669 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1632. Min Act: -0.0001

Data Index: 980617 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1575. Min Act: -0.0000

Data Index: 469103 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1603. Min Act: -0.0000

Data Index: 837834 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1369627 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1574969 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1628929 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1568. Min Act: -0.0001

Data Index: 425162 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1496926 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1032658 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1443323 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1450992 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1585. Min Act: -0.0001

Data Index: 142380 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1540. Min Act: -0.0000

Data Index: 628760 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1340152 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.1976. Min Range: -0.1976

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1382419 (Python Code)

Max Activating Token Index: 413