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

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

Neuron 4336 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1624204 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1653350 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1482917 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1599080 (Python Code)

Max Activating Token Index: 921

Text #4

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1581989 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.8154. Min Act: 0.0000

Data Index: 1388044 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1595193 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1445685 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1512053 (Python Code)

Max Activating Token Index: 379

Text #9

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1417681 (Python Code)

Max Activating Token Index: 862

Text #10

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1411443 (Python Code)

Max Activating Token Index: 298

Text #11

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1535176 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1451368 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1628180 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1561407 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1391739 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1429544 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1514451 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1440727 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 0.9391. Min Range: -0.9391

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1601155 (Python Code)

Max Activating Token Index: 934