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

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

Neuron 5590 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0576. Min Range: -6.0576

Max Act: 6.0576. Min Act: -0.0000

Data Index: 1394776 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 6.0576. Min Range: -6.0576

Max Act: 5.3711. Min Act: -0.0001

Data Index: 1629796 (Python Code)

Max Activating Token Index: 426

Text #2

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.7745. Min Act: -0.0000

Data Index: 1574824 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.9519. Min Act: -0.0000

Data Index: 1477416 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 6.0576. Min Range: -6.0576

Max Act: 5.0916. Min Act: -0.0000

Data Index: 1463293 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 6.0576. Min Range: -6.0576

Max Act: 5.2191. Min Act: -0.0001

Data Index: 1540628 (Python Code)

Max Activating Token Index: 533

Text #6

Max Range: 6.0576. Min Range: -6.0576

Max Act: 5.0292. Min Act: -0.0000

Data Index: 1500555 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.8509. Min Act: -0.0000

Data Index: 1481585 (Python Code)

Max Activating Token Index: 786

Text #8

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.9516. Min Act: -0.0000

Data Index: 1419240 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.9178. Min Act: -0.0000

Data Index: 1535460 (Python Code)

Max Activating Token Index: 891

Text #10

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.3905. Min Act: -0.0000

Data Index: 1470660 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.8713. Min Act: -0.0000

Data Index: 1379830 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.6329. Min Act: -0.0001

Data Index: 1398158 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.7626. Min Act: -0.0000

Data Index: 1650369 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.4060. Min Act: -0.0001

Data Index: 1645664 (Python Code)

Max Activating Token Index: 388

Text #15

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.1587. Min Act: -0.0001

Data Index: 1519032 (Python Code)

Max Activating Token Index: 304

Text #16

Max Range: 6.0576. Min Range: -6.0576

Max Act: 3.8665. Min Act: -0.0000

Data Index: 1458790 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.4682. Min Act: -0.0000

Data Index: 1459352 (Python Code)

Max Activating Token Index: 95

Text #18

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.8073. Min Act: -0.0000

Data Index: 1477696 (Python Code)

Max Activating Token Index: 941

Text #19

Max Range: 6.0576. Min Range: -6.0576

Max Act: 4.6549. Min Act: -0.0000

Data Index: 1599079 (Python Code)

Max Activating Token Index: 860