Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1313619 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0707. Min Act: -0.0001

Data Index: 60956 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0727. Min Act: -0.0001

Data Index: 516680 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0704. Min Act: -0.0001

Data Index: 557457 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0731. Min Act: -0.0001

Data Index: 740195 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1008096 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0718. Min Act: -0.0001

Data Index: 185656 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0001

Data Index: 631427 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1128944 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0688. Min Act: -0.0001

Data Index: 129415 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0760. Min Act: -0.0001

Data Index: 945668 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0707. Min Act: -0.0001

Data Index: 5240 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0703. Min Act: -0.0001

Data Index: 467731 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0680. Min Act: -0.0001

Data Index: 346268 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0723. Min Act: -0.0001

Data Index: 530777 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0683. Min Act: -0.0001

Data Index: 948149 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1170720 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0705. Min Act: -0.0001

Data Index: 204040 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0706. Min Act: -0.0001

Data Index: 162511 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1186171 (C4 (Web Text))

Max Activating Token Index: 296