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

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

Neuron 5768 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1522910 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1489011 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1588168 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1550976 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1609372 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1405375 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1650915 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1489789 (Python Code)

Max Activating Token Index: 442

Text #8

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1465400 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1376259 (Python Code)

Max Activating Token Index: 867

Text #10

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1594585 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1571709 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1628156 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1364356 (Python Code)

Max Activating Token Index: 165

Text #14

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1452317 (Python Code)

Max Activating Token Index: 319

Text #15

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1657081 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1470287 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1599298 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1474764 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1540230 (Python Code)

Max Activating Token Index: 573