Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2596 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.9056. Min Act: -0.0000

Data Index: 1088080 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1009823 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1199991 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.3931. Min Act: -0.0000

Data Index: 627650 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.3390. Min Act: 0.0000

Data Index: 107212 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.3632. Min Act: 0.0000

Data Index: 1084731 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.2293. Min Act: -0.0000

Data Index: 335233 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1131526 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1249860 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.1821. Min Act: -0.0000

Data Index: 97696 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.2003. Min Act: -0.0000

Data Index: 247104 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.2013. Min Act: -0.0000

Data Index: 913524 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.1428. Min Act: 0.0000

Data Index: 861002 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1018421 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1087449 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.1490. Min Act: -0.0000

Data Index: 999742 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.0542. Min Act: -0.0000

Data Index: 283623 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.0547. Min Act: -0.0000

Data Index: 640727 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.0946. Min Act: -0.0000

Data Index: 168788 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.9056. Min Range: -1.9056

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1338364 (C4 (Web Text))

Max Activating Token Index: 845