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

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

Neuron 3721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1545895 (Python Code)

Max Activating Token Index: 182

Text #1

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1578140 (Python Code)

Max Activating Token Index: 289

Text #2

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1450423 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1509818 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1484901 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1437415 (Python Code)

Max Activating Token Index: 955

Text #6

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1431474 (Python Code)

Max Activating Token Index: 376

Text #7

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1501786 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1631670 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1565414 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1562021 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1553909 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1379826 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1369480 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1515049 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1434704 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1562303 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1639363 (Python Code)

Max Activating Token Index: 508

Text #18

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1573758 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 0.2758. Min Range: -0.2758

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1614745 (Python Code)

Max Activating Token Index: 439