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

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

Neuron 905 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: 0.0802. Min Range: -0.0802

Max Act: 0.0802. Min Act: -0.0002

Data Index: 278955 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0729. Min Act: -0.0002

Data Index: 896047 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1136090 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0706. Min Act: -0.0002

Data Index: 903852 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0701. Min Act: -0.0002

Data Index: 359762 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1225384 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0702. Min Act: -0.0002

Data Index: 375791 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1060916 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0665. Min Act: -0.0002

Data Index: 310439 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0661. Min Act: -0.0002

Data Index: 785288 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0662. Min Act: -0.0002

Data Index: 809977 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0656. Min Act: -0.0002

Data Index: 128786 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0672. Min Act: -0.0002

Data Index: 430281 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0637. Min Act: -0.0002

Data Index: 154038 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1202644 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0629. Min Act: -0.0002

Data Index: 850728 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1022404 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0650. Min Act: -0.0002

Data Index: 992043 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0616. Min Act: -0.0002

Data Index: 218068 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0802. Min Range: -0.0802

Max Act: 0.0647. Min Act: -0.0002

Data Index: 820115 (C4 (Web Text))

Max Activating Token Index: 7