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

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

Neuron 1971 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.9353. Min Act: -0.0001

Data Index: 353443 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.9295. Min Act: -0.0001

Data Index: 280743 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7981. Min Act: -0.0001

Data Index: 1282739 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.8894. Min Act: -0.0001

Data Index: 1174778 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7730. Min Act: -0.0001

Data Index: 608966 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.8311. Min Act: -0.0001

Data Index: 715787 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7137. Min Act: -0.0001

Data Index: 1193800 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7990. Min Act: -0.0001

Data Index: 453830 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6797. Min Act: -0.0001

Data Index: 148736 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6850. Min Act: -0.0001

Data Index: 802188 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7572. Min Act: -0.0001

Data Index: 651964 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7569. Min Act: -0.0001

Data Index: 323062 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6642. Min Act: -0.0001

Data Index: 556807 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7455. Min Act: -0.0001

Data Index: 898027 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7416. Min Act: -0.0001

Data Index: 391014 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7260. Min Act: -0.0001

Data Index: 728910 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.7056. Min Act: -0.0001

Data Index: 55134 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6581. Min Act: -0.0001

Data Index: 577618 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6944. Min Act: -0.0001

Data Index: 256161 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.9353. Min Range: -1.9353

Max Act: 1.6866. Min Act: -0.0001

Data Index: 753362 (C4 (Web Text))

Max Activating Token Index: 428