Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0546. Min Act: -0.0001

Data Index: 958790 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0559. Min Act: -0.0000

Data Index: 818853 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0001

Data Index: 650163 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1427809 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1424801 (Python Code)

Max Activating Token Index: 769

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1433338 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0534. Min Act: -0.0000

Data Index: 138801 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0523. Min Act: -0.0000

Data Index: 176467 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0566. Min Act: -0.0001

Data Index: 374934 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0509. Min Act: -0.0001

Data Index: 555201 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0468. Min Act: -0.0001

Data Index: 243640 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1448775 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0505. Min Act: -0.0001

Data Index: 809334 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1295647 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0531. Min Act: -0.0001

Data Index: 964548 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1391230 (Python Code)

Max Activating Token Index: 726

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1470079 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0486. Min Act: -0.0001

Data Index: 298388 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1367871 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0483. Min Act: -0.0000

Data Index: 478918 (C4 (Web Text))

Max Activating Token Index: 354