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

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

Neuron 2626 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1416276 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.7567. Min Act: -0.0000

Data Index: 1627366 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1551969 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1511001 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.4210. Min Act: -0.0000

Data Index: 1556343 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1400493 (Python Code)

Max Activating Token Index: 257

Text #6

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.5033. Min Act: -0.0000

Data Index: 1609353 (Python Code)

Max Activating Token Index: 74

Text #7

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1395852 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1641206 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1373902 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1433379 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.4003. Min Act: -0.0000

Data Index: 1604185 (Python Code)

Max Activating Token Index: 718

Text #12

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.3265. Min Act: -0.0000

Data Index: 1634070 (Python Code)

Max Activating Token Index: 543

Text #13

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.3597. Min Act: -0.0000

Data Index: 1526927 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1651501 (Python Code)

Max Activating Token Index: 499

Text #15

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1430066 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1457310 (Python Code)

Max Activating Token Index: 984

Text #17

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.2406. Min Act: -0.0000

Data Index: 1470834 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1553927 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 1.7797. Min Range: -1.7797

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1501209 (Python Code)

Max Activating Token Index: 384