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

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

Neuron 3980 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1201063 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.6300. Min Act: -0.0000

Data Index: 608622 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1043444 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.3695. Min Act: -0.0000

Data Index: 1064348 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1008563 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.5025. Min Act: -0.0000

Data Index: 181057 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1713. Min Act: -0.0000

Data Index: 973427 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.2104. Min Act: -0.0000

Data Index: 786012 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1259140 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1543. Min Act: -0.0000

Data Index: 174227 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1181. Min Act: -0.0000

Data Index: 900653 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1212663 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1091. Min Act: -0.0000

Data Index: 943446 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0524. Min Act: -0.0000

Data Index: 179593 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1515. Min Act: -0.0000

Data Index: 457587 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0592. Min Act: -0.0000

Data Index: 171365 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1648. Min Act: -0.0000

Data Index: 648963 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1788. Min Act: -0.0000

Data Index: 983516 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1173439 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1877. Min Act: -0.0000

Data Index: 908224 (C4 (Web Text))

Max Activating Token Index: 893