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

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

Neuron 23 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0005

Data Index: 553893 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0880. Min Act: -0.0005

Data Index: 821272 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0845. Min Act: -0.0005

Data Index: 204657 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0850. Min Act: -0.0005

Data Index: 683399 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0818. Min Act: -0.0005

Data Index: 16696 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0791. Min Act: -0.0005

Data Index: 90531 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0771. Min Act: -0.0005

Data Index: 1320474 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0780. Min Act: -0.0005

Data Index: 1058398 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0778. Min Act: -0.0005

Data Index: 557848 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0734. Min Act: -0.0005

Data Index: 284297 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0743. Min Act: -0.0005

Data Index: 260575 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0757. Min Act: -0.0005

Data Index: 653698 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0752. Min Act: -0.0005

Data Index: 1306460 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0734. Min Act: -0.0005

Data Index: 1227193 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0740. Min Act: -0.0005

Data Index: 6618 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0726. Min Act: -0.0004

Data Index: 216842 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0769. Min Act: -0.0005

Data Index: 1105231 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0731. Min Act: -0.0005

Data Index: 749577 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0705. Min Act: -0.0005

Data Index: 1314291 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0718. Min Act: -0.0005

Data Index: 440144 (C4 (Web Text))

Max Activating Token Index: 672