Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 944 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2502. Min Act: -0.0001

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2281. Min Act: -0.0001

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2141. Min Act: -0.0001

Data Index: 534592 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2178. Min Act: -0.0001

Data Index: 705965 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2152. Min Act: -0.0001

Data Index: 750243 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1368153 (Python Code)

Max Activating Token Index: 725

Text #6

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1605057 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1623024 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1508861 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1364385 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1179653 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1626683 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1436612 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1424206 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1470704 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1831. Min Act: -0.0001

Data Index: 139899 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1876. Min Act: -0.0001

Data Index: 597894 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1772. Min Act: -0.0001

Data Index: 954051 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1524806 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1577946 (Python Code)

Max Activating Token Index: 220