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

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

Neuron 5732 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1007936 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1434624 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0584. Min Act: -0.0000

Data Index: 298615 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0593. Min Act: -0.0000

Data Index: 285325 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0592. Min Act: -0.0000

Data Index: 799007 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0608. Min Act: -0.0000

Data Index: 824207 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1459048 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0604. Min Act: -0.0000

Data Index: 357518 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0604. Min Act: -0.0000

Data Index: 64664 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1379246 (Python Code)

Max Activating Token Index: 527

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1517131 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0540. Min Act: -0.0000

Data Index: 322461 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1571995 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1524813 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1409890 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0545. Min Act: -0.0000

Data Index: 893149 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0519. Min Act: -0.0000

Data Index: 621020 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0524. Min Act: -0.0000

Data Index: 390372 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1391236 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0516. Min Act: -0.0000

Data Index: 196600 (C4 (Web Text))

Max Activating Token Index: 856