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

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

Neuron 3827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.9151. Min Act: -0.0001

Data Index: 206300 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.9115. Min Act: -0.0001

Data Index: 408562 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8619. Min Act: -0.0001

Data Index: 602900 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8428. Min Act: -0.0001

Data Index: 1270959 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8382. Min Act: -0.0001

Data Index: 995139 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7949. Min Act: -0.0001

Data Index: 349655 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7860. Min Act: -0.0001

Data Index: 312842 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8139. Min Act: -0.0001

Data Index: 53487 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7839. Min Act: -0.0001

Data Index: 773430 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1218166 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8042. Min Act: -0.0001

Data Index: 62962 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.8048. Min Act: -0.0001

Data Index: 1127859 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7720. Min Act: -0.0001

Data Index: 1117772 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7926. Min Act: -0.0001

Data Index: 1300545 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7599. Min Act: -0.0001

Data Index: 808591 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7614. Min Act: -0.0001

Data Index: 98123 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7766. Min Act: -0.0001

Data Index: 815873 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7723. Min Act: -0.0001

Data Index: 948789 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7906. Min Act: -0.0001

Data Index: 1229413 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.9151. Min Range: -0.9151

Max Act: 0.7484. Min Act: -0.0001

Data Index: 327089 (C4 (Web Text))

Max Activating Token Index: 483