Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5075 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 434268 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1556. Min Act: -0.0001

Data Index: 129356 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1450. Min Act: -0.0001

Data Index: 515230 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1464. Min Act: -0.0001

Data Index: 915602 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1440. Min Act: -0.0001

Data Index: 668690 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1471. Min Act: -0.0001

Data Index: 315585 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1363. Min Act: -0.0001

Data Index: 78596 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1460. Min Act: -0.0001

Data Index: 306439 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1298028 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1041314 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1347. Min Act: -0.0001

Data Index: 557221 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1422. Min Act: -0.0001

Data Index: 54044 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1382. Min Act: -0.0001

Data Index: 1271745 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1414. Min Act: -0.0001

Data Index: 673871 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1459. Min Act: -0.0001

Data Index: 560286 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1024666 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1028591 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1337356 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1402. Min Act: -0.0001

Data Index: 256790 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1292. Min Act: -0.0001

Data Index: 747661 (C4 (Web Text))

Max Activating Token Index: 706