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

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

Neuron 958 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: 1.5542. Min Range: -1.5542

Max Act: 1.5445. Min Act: -0.0001

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.5542. Min Act: -0.0001

Data Index: 694871 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.4420. Min Act: -0.0001

Data Index: 798503 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.4265. Min Act: -0.0001

Data Index: 681659 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.3898. Min Act: -0.0001

Data Index: 771000 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.3330. Min Act: -0.0001

Data Index: 950393 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.3184. Min Act: -0.0001

Data Index: 996315 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2095. Min Act: -0.0001

Data Index: 117513 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2756. Min Act: -0.0001

Data Index: 1103660 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.3032. Min Act: -0.0001

Data Index: 252195 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2475. Min Act: -0.0001

Data Index: 1301248 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2740. Min Act: -0.0001

Data Index: 152263 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2551. Min Act: -0.0001

Data Index: 574882 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2678. Min Act: -0.0001

Data Index: 1249960 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2747. Min Act: -0.0001

Data Index: 863192 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2670. Min Act: -0.0001

Data Index: 1293635 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2283. Min Act: -0.0001

Data Index: 1076735 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1206250 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2192. Min Act: -0.0001

Data Index: 173304 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2876. Min Act: -0.0001

Data Index: 655153 (C4 (Web Text))

Max Activating Token Index: 796