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

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

Neuron 1975 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: 0.4652. Min Range: -0.4652

Max Act: 0.4652. Min Act: -0.0000

Data Index: 467369 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4583. Min Act: -0.0000

Data Index: 653524 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1084057 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4552. Min Act: -0.0000

Data Index: 28885 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1290780 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4340. Min Act: -0.0000

Data Index: 892501 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4123. Min Act: -0.0000

Data Index: 264210 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1114589 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4200. Min Act: -0.0000

Data Index: 102669 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4175. Min Act: -0.0000

Data Index: 157600 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1150772 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4143. Min Act: -0.0000

Data Index: 992001 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1327695 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3838. Min Act: -0.0000

Data Index: 632874 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4039. Min Act: -0.0000

Data Index: 646694 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3572. Min Act: -0.0000

Data Index: 106929 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1337334 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3547. Min Act: -0.0000

Data Index: 864424 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3746. Min Act: -0.0000

Data Index: 718944 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3707. Min Act: -0.0000

Data Index: 862875 (C4 (Web Text))

Max Activating Token Index: 1021