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

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

Neuron 862 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0000

Data Index: 981300 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0555. Min Act: -0.0000

Data Index: 695079 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0572. Min Act: -0.0000

Data Index: 126024 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1348933 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0551. Min Act: -0.0000

Data Index: 700103 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0492. Min Act: -0.0000

Data Index: 136299 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0537. Min Act: -0.0000

Data Index: 63538 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1014061 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1202524 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1328310 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0488. Min Act: -0.0000

Data Index: 582350 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0488. Min Act: -0.0000

Data Index: 30011 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1346941 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0466. Min Act: -0.0000

Data Index: 1319277 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0476. Min Act: -0.0000

Data Index: 22965 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1235817 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1249663 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0491. Min Act: -0.0000

Data Index: 37537 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0457. Min Act: -0.0000

Data Index: 823694 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0455. Min Act: -0.0000

Data Index: 614281 (C4 (Web Text))

Max Activating Token Index: 993