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

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

Neuron 3284 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 500509 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1014. Min Act: -0.0001

Data Index: 134883 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0935. Min Act: -0.0001

Data Index: 150478 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0990. Min Act: -0.0001

Data Index: 411319 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0864. Min Act: -0.0001

Data Index: 305576 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1327780 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0712. Min Act: -0.0001

Data Index: 164293 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0771. Min Act: -0.0001

Data Index: 288875 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1308786 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0689. Min Act: -0.0001

Data Index: 82180 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0662. Min Act: -0.0001

Data Index: 928774 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0749. Min Act: -0.0001

Data Index: 301857 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1122691 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1231215 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0683. Min Act: -0.0001

Data Index: 839751 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0622. Min Act: -0.0001

Data Index: 875867 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1164467 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0598. Min Act: -0.0001

Data Index: 826712 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1051275 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0563. Min Act: -0.0001

Data Index: 835736 (C4 (Web Text))

Max Activating Token Index: 983