Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1423731 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1611152 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1430709 (Python Code)

Max Activating Token Index: 368

Text #3

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1427441 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1443138 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1395497 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1424836 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2390. Min Act: -0.0001

Data Index: 1437373 (Python Code)

Max Activating Token Index: 226

Text #8

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1445453 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2292. Min Act: -0.0001

Data Index: 1392060 (Python Code)

Max Activating Token Index: 488

Text #10

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1369691 (Python Code)

Max Activating Token Index: 1007

Text #11

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1368094 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1508485 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1584866 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1399916 (Python Code)

Max Activating Token Index: 398

Text #15

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1494911 (Python Code)

Max Activating Token Index: 430

Text #16

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2114. Min Act: 0.0000

Data Index: 1534908 (Python Code)

Max Activating Token Index: 507

Text #17

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1365765 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1551653 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 0.2800. Min Range: -0.2800

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1626215 (Python Code)

Max Activating Token Index: 744