Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 652 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5722. Min Act: -0.0002

Data Index: 885001 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3963. Min Act: -0.0002

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4168. Min Act: -0.0002

Data Index: 981007 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4340. Min Act: -0.0002

Data Index: 469207 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3817. Min Act: -0.0002

Data Index: 1087745 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4060. Min Act: -0.0002

Data Index: 648033 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3972. Min Act: -0.0002

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3743. Min Act: -0.0002

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3935. Min Act: -0.0002

Data Index: 149222 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4106. Min Act: -0.0002

Data Index: 340788 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3924. Min Act: -0.0002

Data Index: 1230246 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3688. Min Act: -0.0002

Data Index: 211626 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3534. Min Act: -0.0002

Data Index: 478467 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3743. Min Act: -0.0002

Data Index: 1005584 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3992. Min Act: -0.0002

Data Index: 518390 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3710. Min Act: -0.0002

Data Index: 892694 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3486. Min Act: -0.0002

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3666. Min Act: -0.0001

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3834. Min Act: -0.0002

Data Index: 1021947 (C4 (Web Text))

Max Activating Token Index: 825