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

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

Neuron 4707 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1555464 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1639533 (Python Code)

Max Activating Token Index: 900

Text #2

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1563177 (Python Code)

Max Activating Token Index: 581

Text #3

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1359901 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1441383 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1551935 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1360762 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1440363 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1396058 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1458077 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1433689 (Python Code)

Max Activating Token Index: 524

Text #11

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1629542 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1561867 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1400546 (Python Code)

Max Activating Token Index: 526

Text #14

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1612206 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1366459 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2994. Min Act: -0.0000

Data Index: 1463043 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1566731 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1404152 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 1.5461. Min Range: -1.5461

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1584855 (Python Code)

Max Activating Token Index: 313