Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0002

Data Index: 464680 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1255620 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0604. Min Act: -0.0003

Data Index: 278560 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1034070 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1053472 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0587. Min Act: -0.0003

Data Index: 909364 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0579. Min Act: -0.0003

Data Index: 56435 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0577. Min Act: -0.0003

Data Index: 442571 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0571. Min Act: -0.0003

Data Index: 414487 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0579. Min Act: -0.0004

Data Index: 109965 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0586. Min Act: -0.0003

Data Index: 768704 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0585. Min Act: -0.0003

Data Index: 68756 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1120801 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0574. Min Act: -0.0003

Data Index: 22715 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0561. Min Act: -0.0003

Data Index: 930809 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1303562 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0558. Min Act: -0.0003

Data Index: 776713 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1095389 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0546. Min Act: -0.0003

Data Index: 440915 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0552. Min Act: -0.0002

Data Index: 596090 (C4 (Web Text))

Max Activating Token Index: 937