Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.5032. Min Range: -4.5032

Max Act: 4.5032. Min Act: -0.0001

Data Index: 502158 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 4.5032. Min Range: -4.5032

Max Act: 4.0969. Min Act: -0.0001

Data Index: 1275874 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 4.5032. Min Range: -4.5032

Max Act: 4.3328. Min Act: -0.0001

Data Index: 22557 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.9970. Min Act: -0.0001

Data Index: 521978 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.8615. Min Act: -0.0000

Data Index: 855580 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.9654. Min Act: -0.0001

Data Index: 911785 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.9016. Min Act: -0.0001

Data Index: 680638 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.8973. Min Act: -0.0001

Data Index: 912223 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.6802. Min Act: -0.0001

Data Index: 222264 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.7945. Min Act: -0.0001

Data Index: 317338 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.4532. Min Act: -0.0000

Data Index: 340620 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.5969. Min Act: -0.0001

Data Index: 1041310 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.5536. Min Act: -0.0001

Data Index: 922790 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.4882. Min Act: -0.0001

Data Index: 602808 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.2874. Min Act: -0.0001

Data Index: 490869 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.5277. Min Act: -0.0001

Data Index: 957870 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.2908. Min Act: -0.0001

Data Index: 676655 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.2944. Min Act: -0.0001

Data Index: 913132 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.2704. Min Act: -0.0001

Data Index: 1351398 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 4.5032. Min Range: -4.5032

Max Act: 3.0723. Min Act: -0.0001

Data Index: 1229670 (C4 (Web Text))

Max Activating Token Index: 737