Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 575 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1262. Min Act: -0.0003

Data Index: 1341375 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1273. Min Act: -0.0003

Data Index: 495087 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0997. Min Act: -0.0003

Data Index: 427287 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0999. Min Act: -0.0003

Data Index: 763916 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0970. Min Act: -0.0003

Data Index: 729834 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0940. Min Act: -0.0003

Data Index: 479048 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1269645 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1065138 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0845. Min Act: -0.0003

Data Index: 1092671 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0818. Min Act: -0.0003

Data Index: 202436 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0810. Min Act: -0.0003

Data Index: 466708 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0806. Min Act: -0.0003

Data Index: 354482 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0797. Min Act: -0.0003

Data Index: 311269 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0776. Min Act: -0.0003

Data Index: 285564 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0737. Min Act: -0.0003

Data Index: 570640 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0763. Min Act: -0.0003

Data Index: 38834 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0743. Min Act: -0.0003

Data Index: 774554 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0743. Min Act: -0.0003

Data Index: 843660 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1045370 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0726. Min Act: -0.0003

Data Index: 146683 (C4 (Web Text))

Max Activating Token Index: 270