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

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

Neuron 1589 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1088434 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0569. Min Act: -0.0001

Data Index: 327201 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0516. Min Act: -0.0000

Data Index: 1051180 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1287160 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0512. Min Act: -0.0001

Data Index: 75921 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0511. Min Act: -0.0001

Data Index: 938063 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0513. Min Act: -0.0001

Data Index: 361522 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0468. Min Act: -0.0001

Data Index: 646640 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1344099 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0454. Min Act: -0.0001

Data Index: 814740 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1171349 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1165108 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0527. Min Act: -0.0001

Data Index: 423250 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1063472 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0457. Min Act: -0.0001

Data Index: 671833 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0459. Min Act: -0.0001

Data Index: 107418 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0491. Min Act: -0.0001

Data Index: 309146 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1469539 (Python Code)

Max Activating Token Index: 277

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0452. Min Act: -0.0001

Data Index: 721949 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0464. Min Act: -0.0001

Data Index: 185967 (C4 (Web Text))

Max Activating Token Index: 10