Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3810 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1261363 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2573. Min Act: -0.0000

Data Index: 205136 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2505. Min Act: -0.0000

Data Index: 921915 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1562871 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1625. Min Act: -0.0000

Data Index: 644565 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1540. Min Act: -0.0000

Data Index: 477011 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1448. Min Act: -0.0000

Data Index: 870826 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1009422 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1536424 (Python Code)

Max Activating Token Index: 953

Text #9

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1424. Min Act: -0.0000

Data Index: 841662 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1289951 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1279. Min Act: -0.0000

Data Index: 603092 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1334908 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1403. Min Act: -0.0000

Data Index: 51296 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1351. Min Act: -0.0000

Data Index: 529743 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1384. Min Act: -0.0000

Data Index: 291492 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1401. Min Act: -0.0000

Data Index: 194386 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1497668 (Python Code)

Max Activating Token Index: 390

Text #18

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1492766 (Python Code)

Max Activating Token Index: 978

Text #19

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1168785 (C4 (Web Text))

Max Activating Token Index: 992