Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1859 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1133386 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0828. Min Act: -0.0002

Data Index: 256916 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1561085 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0837. Min Act: -0.0002

Data Index: 22301 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1395412 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1487374 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1513062 (Python Code)

Max Activating Token Index: 358

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0779. Min Act: -0.0001

Data Index: 721243 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0743. Min Act: -0.0001

Data Index: 836189 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1375922 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0720. Min Act: -0.0001

Data Index: 858197 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0757. Min Act: -0.0002

Data Index: 909875 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0707. Min Act: -0.0002

Data Index: 97833 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1493551 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0729. Min Act: -0.0001

Data Index: 238515 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0730. Min Act: -0.0002

Data Index: 60733 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0671. Min Act: -0.0002

Data Index: 277728 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0722. Min Act: -0.0002

Data Index: 124014 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0668. Min Act: -0.0002

Data Index: 325642 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1006761 (C4 (Web Text))

Max Activating Token Index: 528