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

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

Neuron 3313 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1898. Min Act: -0.0000

Data Index: 601184 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1923. Min Act: -0.0001

Data Index: 389685 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1033518 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1636. Min Act: -0.0001

Data Index: 262510 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1512. Min Act: -0.0001

Data Index: 220722 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1637. Min Act: -0.0000

Data Index: 422346 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1551. Min Act: -0.0000

Data Index: 658972 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1168561 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1506. Min Act: -0.0000

Data Index: 613747 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1538. Min Act: -0.0001

Data Index: 109680 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1495. Min Act: -0.0000

Data Index: 995596 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1445. Min Act: -0.0000

Data Index: 353486 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1510. Min Act: -0.0001

Data Index: 96156 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1382. Min Act: -0.0001

Data Index: 878726 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1382. Min Act: -0.0000

Data Index: 771203 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1312. Min Act: -0.0001

Data Index: 8798 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1228. Min Act: -0.0001

Data Index: 673652 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1329. Min Act: -0.0001

Data Index: 504181 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1301. Min Act: -0.0000

Data Index: 89298 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.1923. Min Range: -0.1923

Max Act: 0.1287. Min Act: -0.0001

Data Index: 159006 (C4 (Web Text))

Max Activating Token Index: 891