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

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

Neuron 546 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: 1.4429. Min Range: -1.4429

Max Act: 1.4429. Min Act: -0.0001

Data Index: 1616330 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.9911. Min Act: -0.0001

Data Index: 1530300 (Python Code)

Max Activating Token Index: 491

Text #2

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1488935 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.9768. Min Act: -0.0001

Data Index: 1589758 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8698. Min Act: -0.0001

Data Index: 1619240 (Python Code)

Max Activating Token Index: 530

Text #5

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1411546 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1396588 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1647733 (Python Code)

Max Activating Token Index: 852

Text #8

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.9099. Min Act: -0.0001

Data Index: 1394161 (Python Code)

Max Activating Token Index: 944

Text #9

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1580226 (Python Code)

Max Activating Token Index: 778

Text #10

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1633831 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1629678 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8136. Min Act: -0.0001

Data Index: 1560941 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1627462 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1387034 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1464127 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.7900. Min Act: -0.0001

Data Index: 1654781 (Python Code)

Max Activating Token Index: 361

Text #17

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.7740. Min Act: -0.0001

Data Index: 1563718 (Python Code)

Max Activating Token Index: 457

Text #18

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1619471 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 1.4429. Min Range: -1.4429

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1614907 (Python Code)

Max Activating Token Index: 135