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

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

Neuron 2988 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: 5.8881. Min Range: -5.8881

Max Act: 5.8881. Min Act: -0.0001

Data Index: 362252 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.8488. Min Act: -0.0001

Data Index: 714698 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.6899. Min Act: -0.0001

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.3736. Min Act: -0.0001

Data Index: 475291 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.3228. Min Act: -0.0001

Data Index: 1032363 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.1271. Min Act: -0.0001

Data Index: 572161 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.2857. Min Act: -0.0001

Data Index: 161682 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.2811. Min Act: -0.0001

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.2250. Min Act: -0.0001

Data Index: 987798 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.2410. Min Act: -0.0001

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.1770. Min Act: -0.0001

Data Index: 314490 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 5.8881. Min Range: -5.8881

Max Act: 4.9931. Min Act: -0.0000

Data Index: 846664 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.1820. Min Act: -0.0001

Data Index: 1021270 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.1750. Min Act: -0.0001

Data Index: 495781 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.3184. Min Act: -0.0001

Data Index: 682078 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 5.8881. Min Range: -5.8881

Max Act: 4.9435. Min Act: -0.0001

Data Index: 699596 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 5.8881. Min Range: -5.8881

Max Act: 5.2188. Min Act: -0.0001

Data Index: 216967 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 5.8881. Min Range: -5.8881

Max Act: 4.9767. Min Act: -0.0001

Data Index: 1224703 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 5.8881. Min Range: -5.8881

Max Act: 4.9904. Min Act: -0.0001

Data Index: 2350 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 5.8881. Min Range: -5.8881

Max Act: 4.9572. Min Act: -0.0001

Data Index: 224148 (C4 (Web Text))

Max Activating Token Index: 664