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

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

Neuron 570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1526670 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1524411 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1489524 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1550179 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1410580 (Python Code)

Max Activating Token Index: 66

Text #5

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1542229 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1988. Min Act: 0.0001

Data Index: 1403040 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2024. Min Act: -0.0001

Data Index: 1482634 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1453418 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1454055 (Python Code)

Max Activating Token Index: 195

Text #10

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1401027 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1610438 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1956. Min Act: 0.0002

Data Index: 1498625 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1629853 (Python Code)

Max Activating Token Index: 144

Text #14

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1631776 (Python Code)

Max Activating Token Index: 556

Text #15

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1628920 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1637027 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1810. Min Act: 0.0002

Data Index: 1587031 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1506414 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1387324 (Python Code)

Max Activating Token Index: 431