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

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

Neuron 186 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: 4.2803. Min Range: -4.2803

Max Act: 4.2803. Min Act: -0.0000

Data Index: 894399 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 4.2803. Min Range: -4.2803

Max Act: 3.3739. Min Act: -0.0000

Data Index: 1128900 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 4.2803. Min Range: -4.2803

Max Act: 3.4828. Min Act: -0.0000

Data Index: 481511 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 4.2803. Min Range: -4.2803

Max Act: 3.3306. Min Act: -0.0000

Data Index: 667197 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 4.2803. Min Range: -4.2803

Max Act: 3.3669. Min Act: -0.0000

Data Index: 800841 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 4.2803. Min Range: -4.2803

Max Act: 3.1592. Min Act: -0.0000

Data Index: 224060 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 4.2803. Min Range: -4.2803

Max Act: 3.2186. Min Act: -0.0000

Data Index: 1295103 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.9986. Min Act: -0.0000

Data Index: 330309 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.9051. Min Act: -0.0000

Data Index: 561909 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.6995. Min Act: -0.0000

Data Index: 744525 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.8107. Min Act: -0.0000

Data Index: 453747 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.7954. Min Act: -0.0000

Data Index: 1079656 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.8016. Min Act: -0.0000

Data Index: 1322910 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.5995. Min Act: -0.0000

Data Index: 1061536 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.6823. Min Act: -0.0000

Data Index: 572976 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.5373. Min Act: -0.0000

Data Index: 140346 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.5012. Min Act: -0.0000

Data Index: 869319 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.3769. Min Act: -0.0000

Data Index: 1255875 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.6094. Min Act: -0.0000

Data Index: 1185649 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 4.2803. Min Range: -4.2803

Max Act: 2.4614. Min Act: -0.0000

Data Index: 100429 (C4 (Web Text))

Max Activating Token Index: 812