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

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

Neuron 4454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4558. Min Act: -0.0001

Data Index: 598497 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.7184. Min Act: -0.0001

Data Index: 120975 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.3797. Min Act: -0.0001

Data Index: 968235 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.1711. Min Act: -0.0001

Data Index: 613481 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.1745. Min Act: -0.0001

Data Index: 1350641 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.8113. Min Act: -0.0001

Data Index: 689891 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.0900. Min Act: -0.0001

Data Index: 1058782 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.8905. Min Act: -0.0001

Data Index: 1020233 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.0313. Min Act: -0.0001

Data Index: 506846 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.8943. Min Act: -0.0001

Data Index: 998944 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.9923. Min Act: -0.0001

Data Index: 1095301 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.9916. Min Act: -0.0001

Data Index: 419114 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.6521. Min Act: -0.0001

Data Index: 270249 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.3088. Min Act: -0.0001

Data Index: 1044410 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.1164. Min Act: -0.0001

Data Index: 1206609 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.9266. Min Act: -0.0001

Data Index: 1073570 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.8345. Min Act: -0.0001

Data Index: 1008863 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.6693. Min Act: -0.0001

Data Index: 557560 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.7713. Min Act: -0.0001

Data Index: 174639 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 4.7184. Min Range: -4.7184

Max Act: 3.5672. Min Act: -0.0001

Data Index: 466743 (C4 (Web Text))

Max Activating Token Index: 678