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

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

Neuron 4906 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1626. Min Act: -0.0000

Data Index: 697440 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1115579 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1542. Min Act: -0.0000

Data Index: 742976 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1536. Min Act: -0.0000

Data Index: 629785 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1574. Min Act: -0.0000

Data Index: 924156 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1026509 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1116848 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1124958 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1469. Min Act: -0.0000

Data Index: 925538 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1505. Min Act: -0.0000

Data Index: 671910 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1498. Min Act: -0.0000

Data Index: 855585 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1326357 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1445. Min Act: -0.0000

Data Index: 506116 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1419. Min Act: -0.0000

Data Index: 283108 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1117709 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1416. Min Act: -0.0000

Data Index: 818765 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1455. Min Act: -0.0000

Data Index: 414603 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1364. Min Act: -0.0000

Data Index: 314592 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1284619 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1383. Min Act: -0.0000

Data Index: 211966 (C4 (Web Text))

Max Activating Token Index: 411