Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1007 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0003

Data Index: 956065 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1161699 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1356650 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0529. Min Act: -0.0003

Data Index: 368543 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0520. Min Act: -0.0003

Data Index: 55876 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1341891 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0491. Min Act: -0.0003

Data Index: 480479 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1283046 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0476. Min Act: -0.0003

Data Index: 797762 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0488. Min Act: -0.0003

Data Index: 368357 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0492. Min Act: -0.0004

Data Index: 1344637 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0494. Min Act: -0.0003

Data Index: 618582 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0460. Min Act: -0.0003

Data Index: 784732 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0474. Min Act: -0.0003

Data Index: 865502 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0488. Min Act: -0.0003

Data Index: 504109 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1305564 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1136598 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0453. Min Act: -0.0003

Data Index: 284482 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0459. Min Act: -0.0004

Data Index: 1170187 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0458. Min Act: -0.0003

Data Index: 581956 (C4 (Web Text))

Max Activating Token Index: 84