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

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

Neuron 4452 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: 3.7813. Min Range: -3.7813

Max Act: 3.4573. Min Act: -0.0000

Data Index: 1459022 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.1706. Min Act: -0.0000

Data Index: 1566951 (Python Code)

Max Activating Token Index: 202

Text #2

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.7813. Min Act: -0.0000

Data Index: 1385244 (Python Code)

Max Activating Token Index: 231

Text #3

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.2412. Min Act: -0.0000

Data Index: 1547489 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.8250. Min Act: -0.0000

Data Index: 1431537 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.8405. Min Act: 0.0000

Data Index: 287925 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.7813. Min Range: -3.7813

Max Act: 3.1820. Min Act: -0.0000

Data Index: 1443751 (Python Code)

Max Activating Token Index: 320

Text #7

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.5963. Min Act: 0.0000

Data Index: 80519 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.6035. Min Act: -0.0000

Data Index: 1558298 (Python Code)

Max Activating Token Index: 238

Text #9

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.5880. Min Act: -0.0000

Data Index: 1622414 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.7014. Min Act: -0.0000

Data Index: 225235 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.6140. Min Act: -0.0000

Data Index: 1650545 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.5891. Min Act: -0.0000

Data Index: 629956 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.5679. Min Act: -0.0000

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.7164. Min Act: -0.0000

Data Index: 1356709 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.5305. Min Act: -0.0000

Data Index: 1363596 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1366586 (Python Code)

Max Activating Token Index: 468

Text #17

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.4331. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.4030. Min Act: -0.0000

Data Index: 1612974 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 3.7813. Min Range: -3.7813

Max Act: 2.2457. Min Act: -0.0000

Data Index: 1588783 (Python Code)

Max Activating Token Index: 726