Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1154765 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0544. Min Act: -0.0001

Data Index: 544409 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0595. Min Act: -0.0001

Data Index: 405130 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0574. Min Act: -0.0001

Data Index: 241653 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0530. Min Act: -0.0001

Data Index: 480343 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0482. Min Act: -0.0001

Data Index: 275145 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0485. Min Act: -0.0001

Data Index: 124283 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0491. Min Act: -0.0001

Data Index: 823364 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0497. Min Act: -0.0001

Data Index: 438314 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1097540 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0479. Min Act: -0.0001

Data Index: 603960 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0462. Min Act: -0.0001

Data Index: 862526 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1506868 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0458. Min Act: -0.0001

Data Index: 530035 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0448. Min Act: -0.0001

Data Index: 357770 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0441. Min Act: -0.0001

Data Index: 472229 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0441. Min Act: -0.0001

Data Index: 329982 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0491. Min Act: -0.0001

Data Index: 9022 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1252214 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1085501 (C4 (Web Text))

Max Activating Token Index: 569