Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0968. Min Act: -0.0001

Data Index: 425241 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0914. Min Act: -0.0001

Data Index: 329992 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0743. Min Act: -0.0001

Data Index: 610545 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0781. Min Act: -0.0001

Data Index: 959568 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0790. Min Act: -0.0001

Data Index: 877737 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1048617 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0657. Min Act: -0.0001

Data Index: 176619 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0667. Min Act: -0.0001

Data Index: 657615 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0755. Min Act: -0.0001

Data Index: 236739 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0664. Min Act: -0.0001

Data Index: 677942 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1003641 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0652. Min Act: -0.0001

Data Index: 786147 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1161577 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0656. Min Act: -0.0001

Data Index: 594986 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0670. Min Act: -0.0001

Data Index: 304404 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0598. Min Act: -0.0001

Data Index: 345088 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0619. Min Act: -0.0001

Data Index: 892463 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0598. Min Act: -0.0001

Data Index: 857411 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1308746 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0968. Min Range: -0.0968

Max Act: 0.0594. Min Act: -0.0001

Data Index: 224575 (C4 (Web Text))

Max Activating Token Index: 21