Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 564 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.9307. Min Act: -0.0000

Data Index: 1580005 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.8159. Min Act: -0.0000

Data Index: 1409316 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.5813. Min Act: -0.0000

Data Index: 1577369 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1486594 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.4315. Min Act: -0.0000

Data Index: 1363115 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2560. Min Act: -0.0000

Data Index: 1494026 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3724. Min Act: -0.0000

Data Index: 1548371 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3549. Min Act: -0.0000

Data Index: 1577966 (Python Code)

Max Activating Token Index: 779

Text #8

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2444. Min Act: -0.0000

Data Index: 1574685 (Python Code)

Max Activating Token Index: 505

Text #9

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3355. Min Act: -0.0000

Data Index: 1462232 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.3291. Min Act: -0.0000

Data Index: 1396352 (Python Code)

Max Activating Token Index: 542

Text #11

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.4483. Min Act: -0.0000

Data Index: 1382062 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1613914 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1499706 (Python Code)

Max Activating Token Index: 703

Text #14

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.4775. Min Act: -0.0000

Data Index: 1577143 (Python Code)

Max Activating Token Index: 713

Text #15

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2064. Min Act: -0.0000

Data Index: 1626643 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1457022 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.2060. Min Act: -0.0000

Data Index: 1400998 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.0951. Min Act: -0.0000

Data Index: 1606347 (Python Code)

Max Activating Token Index: 223

Text #19

Max Range: 2.9307. Min Range: -2.9307

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1647524 (Python Code)

Max Activating Token Index: 612