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

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

Neuron 4897 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1522871 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1382028 (Python Code)

Max Activating Token Index: 684

Text #2

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0828. Min Act: -0.0000

Data Index: 248297 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1644669 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1384687 (Python Code)

Max Activating Token Index: 196

Text #5

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0694. Min Act: -0.0000

Data Index: 461069 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1305753 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.3769. Min Range: -1.3769

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1655632 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9829. Min Act: -0.0000

Data Index: 366560 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1501751 (Python Code)

Max Activating Token Index: 292

Text #10

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9832. Min Act: -0.0000

Data Index: 339015 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1409922 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1418640 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8529. Min Act: -0.0000

Data Index: 642278 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8528. Min Act: -0.0000

Data Index: 516592 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1457464 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1250875 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1603043 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1639392 (Python Code)

Max Activating Token Index: 409

Text #19

Max Range: 1.3769. Min Range: -1.3769

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1594084 (Python Code)

Max Activating Token Index: 97