Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5291 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.9841. Min Act: -0.0000

Data Index: 1486992 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7760. Min Act: -0.0000

Data Index: 873525 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7445. Min Act: -0.0000

Data Index: 1586960 (Python Code)

Max Activating Token Index: 807

Text #3

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.6967. Min Act: -0.0000

Data Index: 663664 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.7144. Min Act: -0.0000

Data Index: 1417042 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.5653. Min Act: 0.0000

Data Index: 1243317 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.4621. Min Act: -0.0000

Data Index: 99265 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.4972. Min Act: -0.0000

Data Index: 955406 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.5920. Min Act: -0.0000

Data Index: 1325558 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1270028 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1557769 (Python Code)

Max Activating Token Index: 1002

Text #11

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.4913. Min Act: -0.0000

Data Index: 177317 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.3931. Min Act: -0.0000

Data Index: 932856 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1495986 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1647437 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1428614 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1466915 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.3001. Min Act: -0.0000

Data Index: 771418 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1445644 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 1.9841. Min Range: -1.9841

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1302892 (C4 (Web Text))

Max Activating Token Index: 967