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

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

Neuron 4439 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0002

Data Index: 599926 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0678. Min Act: -0.0002

Data Index: 616820 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0646. Min Act: -0.0002

Data Index: 244621 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0657. Min Act: -0.0002

Data Index: 388162 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0671. Min Act: -0.0002

Data Index: 89238 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0656. Min Act: -0.0002

Data Index: 686988 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0682. Min Act: -0.0002

Data Index: 481913 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0653. Min Act: -0.0002

Data Index: 212253 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0630. Min Act: -0.0002

Data Index: 875713 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0682. Min Act: -0.0002

Data Index: 636919 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0620. Min Act: -0.0002

Data Index: 483674 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0689. Min Act: -0.0002

Data Index: 265064 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0653. Min Act: -0.0002

Data Index: 919439 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1052368 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0665. Min Act: -0.0002

Data Index: 913474 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1146227 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1244786 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0627. Min Act: -0.0002

Data Index: 683231 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1131558 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1249080 (C4 (Web Text))

Max Activating Token Index: 856