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

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

Neuron 4595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.7244. Min Act: -0.0000

Data Index: 1115787 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.8591. Min Act: -0.0000

Data Index: 456329 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.7191. Min Act: -0.0000

Data Index: 1273629 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.6459. Min Act: -0.0000

Data Index: 483680 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.5409. Min Act: -0.0000

Data Index: 65417 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.5580. Min Act: -0.0000

Data Index: 1480174 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.4889. Min Act: -0.0000

Data Index: 656672 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3211. Min Act: -0.0000

Data Index: 1455109 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3180. Min Act: -0.0000

Data Index: 1635637 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.4505. Min Act: -0.0000

Data Index: 1458657 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.4411. Min Act: -0.0000

Data Index: 1640015 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3121. Min Act: -0.0000

Data Index: 1633161 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.4296. Min Act: -0.0000

Data Index: 1619969 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.4106. Min Act: -0.0000

Data Index: 1446402 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3001. Min Act: -0.0000

Data Index: 1412152 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3298. Min Act: -0.0000

Data Index: 1496575 (Python Code)

Max Activating Token Index: 540

Text #16

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.1050. Min Act: -0.0000

Data Index: 1644998 (Python Code)

Max Activating Token Index: 333

Text #17

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.2091. Min Act: -0.0000

Data Index: 1468013 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3226. Min Act: -0.0000

Data Index: 1363014 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 2.8591. Min Range: -2.8591

Max Act: 2.3155. Min Act: -0.0000

Data Index: 1369712 (Python Code)

Max Activating Token Index: 221