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

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

Neuron 3541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4972. Min Act: -0.0001

Data Index: 1004783 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2839. Min Act: -0.0001

Data Index: 1447871 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3641. Min Act: -0.0001

Data Index: 1588467 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1596496 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1581051 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2439. Min Act: -0.0000

Data Index: 1518438 (Python Code)

Max Activating Token Index: 826

Text #6

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1620144 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1570041 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1533205 (Python Code)

Max Activating Token Index: 588

Text #9

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1368508 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1421690 (Python Code)

Max Activating Token Index: 561

Text #11

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1389672 (Python Code)

Max Activating Token Index: 732

Text #12

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1497761 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1588292 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1298. Min Act: -0.0000

Data Index: 1512935 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1603646 (Python Code)

Max Activating Token Index: 332

Text #16

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1632112 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1455692 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1585454 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1389284 (Python Code)

Max Activating Token Index: 618