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

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

Neuron 3925 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: 2.5089. Min Range: -2.5089

Max Act: 2.5089. Min Act: -0.0000

Data Index: 644529 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.2040. Min Act: -0.0000

Data Index: 1203875 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.3682. Min Act: -0.0000

Data Index: 454006 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.2248. Min Act: -0.0000

Data Index: 971926 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.9870. Min Act: -0.0000

Data Index: 130532 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0072. Min Act: -0.0000

Data Index: 4424 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1140968 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0061. Min Act: -0.0000

Data Index: 50216 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.9953. Min Act: -0.0000

Data Index: 203841 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.8865. Min Act: -0.0000

Data Index: 598624 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.8854. Min Act: -0.0000

Data Index: 43232 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.8851. Min Act: -0.0000

Data Index: 681315 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.9896. Min Act: -0.0000

Data Index: 566306 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.8809. Min Act: -0.0000

Data Index: 1317102 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1071326 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0450. Min Act: -0.0000

Data Index: 536730 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0345. Min Act: -0.0000

Data Index: 40177 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0355. Min Act: -0.0000

Data Index: 578793 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 2.5089. Min Range: -2.5089

Max Act: 2.0092. Min Act: -0.0000

Data Index: 1322311 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 2.5089. Min Range: -2.5089

Max Act: 1.8073. Min Act: -0.0000

Data Index: 132315 (C4 (Web Text))

Max Activating Token Index: 678