Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2306 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1961. Min Act: -0.0001

Data Index: 297837 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1988. Min Act: -0.0001

Data Index: 45106 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1941. Min Act: -0.0001

Data Index: 26876 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1781. Min Act: -0.0001

Data Index: 567355 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1781. Min Act: -0.0001

Data Index: 910989 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1746. Min Act: -0.0001

Data Index: 80875 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1751. Min Act: -0.0001

Data Index: 831473 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1672. Min Act: -0.0001

Data Index: 756233 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1612. Min Act: -0.0001

Data Index: 849812 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1591. Min Act: -0.0001

Data Index: 939389 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1271619 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1585. Min Act: -0.0001

Data Index: 5520 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1558. Min Act: -0.0001

Data Index: 723408 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1543. Min Act: -0.0001

Data Index: 1127208 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1633. Min Act: -0.0001

Data Index: 789292 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1022765 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1665. Min Act: -0.0001

Data Index: 806725 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1554. Min Act: -0.0001

Data Index: 618681 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1988. Min Range: -0.1988

Max Act: 0.1536. Min Act: -0.0001

Data Index: 662232 (C4 (Web Text))

Max Activating Token Index: 86