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

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

Neuron 1494 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2433. Min Act: -0.0000

Data Index: 258825 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2211. Min Act: -0.0000

Data Index: 824630 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1836. Min Act: -0.0000

Data Index: 266478 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1685. Min Act: -0.0000

Data Index: 797954 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1643. Min Act: -0.0000

Data Index: 154550 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1790. Min Act: -0.0000

Data Index: 759544 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1655. Min Act: -0.0000

Data Index: 559058 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1610. Min Act: -0.0000

Data Index: 77293 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1558. Min Act: -0.0000

Data Index: 680547 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1555. Min Act: -0.0000

Data Index: 626403 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1629. Min Act: -0.0000

Data Index: 668612 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1427. Min Act: -0.0000

Data Index: 969089 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1023766 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1395. Min Act: -0.0000

Data Index: 473063 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1605. Min Act: -0.0000

Data Index: 249257 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1426. Min Act: -0.0000

Data Index: 134654 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1195546 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1497580 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1188670 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1123710 (C4 (Web Text))

Max Activating Token Index: 341