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

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

Neuron 1045 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: 1.9718. Min Range: -1.9718

Max Act: 1.9718. Min Act: -0.0001

Data Index: 503718 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.8481. Min Act: -0.0001

Data Index: 813127 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.8625. Min Act: -0.0001

Data Index: 736317 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.6365. Min Act: -0.0001

Data Index: 1238705 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.6106. Min Act: -0.0001

Data Index: 1061665 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.6906. Min Act: -0.0001

Data Index: 274882 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.7988. Min Act: -0.0001

Data Index: 931801 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.6736. Min Act: -0.0001

Data Index: 971467 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5820. Min Act: -0.0001

Data Index: 904110 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5787. Min Act: -0.0001

Data Index: 943276 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.7762. Min Act: -0.0001

Data Index: 894576 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5574. Min Act: -0.0001

Data Index: 371376 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5547. Min Act: -0.0001

Data Index: 1028544 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.8389. Min Act: -0.0001

Data Index: 110706 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.6524. Min Act: -0.0001

Data Index: 569359 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5506. Min Act: -0.0001

Data Index: 453214 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.6387. Min Act: -0.0001

Data Index: 1065785 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5979. Min Act: -0.0001

Data Index: 380166 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5236. Min Act: -0.0001

Data Index: 1183101 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.9718. Min Range: -1.9718

Max Act: 1.5985. Min Act: -0.0001

Data Index: 1052877 (C4 (Web Text))

Max Activating Token Index: 897