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

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

Neuron 3564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3764. Min Range: -1.3764

Max Act: 1.3764. Min Act: -0.0001

Data Index: 908635 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9963. Min Act: -0.0001

Data Index: 9216 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.3764. Min Range: -1.3764

Max Act: 1.0268. Min Act: -0.0001

Data Index: 25786 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.3764. Min Range: -1.3764

Max Act: 1.0370. Min Act: -0.0001

Data Index: 101565 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9659. Min Act: -0.0001

Data Index: 895737 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8260. Min Act: -0.0001

Data Index: 783640 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8937. Min Act: -0.0001

Data Index: 325983 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8619. Min Act: -0.0001

Data Index: 4730 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9182. Min Act: -0.0001

Data Index: 454711 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9064. Min Act: -0.0001

Data Index: 115658 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8721. Min Act: -0.0001

Data Index: 884653 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9012. Min Act: -0.0001

Data Index: 149004 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9246. Min Act: -0.0001

Data Index: 725450 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9680. Min Act: -0.0001

Data Index: 944733 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8893. Min Act: -0.0001

Data Index: 716569 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8929. Min Act: -0.0001

Data Index: 639674 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8888. Min Act: -0.0001

Data Index: 22566 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.6028. Min Act: -0.0001

Data Index: 75501 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.9445. Min Act: -0.0001

Data Index: 966969 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.3764. Min Range: -1.3764

Max Act: 0.8183. Min Act: -0.0001

Data Index: 904978 (C4 (Web Text))

Max Activating Token Index: 204