Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3465 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.9729. Min Act: -0.0001

Data Index: 1525386 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.6642. Min Act: -0.0001

Data Index: 1397501 (Python Code)

Max Activating Token Index: 735

Text #2

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.9070. Min Act: -0.0001

Data Index: 1478729 (Python Code)

Max Activating Token Index: 583

Text #3

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.7546. Min Act: -0.0001

Data Index: 1450541 (Python Code)

Max Activating Token Index: 591

Text #4

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8148. Min Act: -0.0001

Data Index: 1384399 (Python Code)

Max Activating Token Index: 487

Text #5

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8262. Min Act: -0.0001

Data Index: 1378460 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8171. Min Act: -0.0001

Data Index: 1384440 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.7664. Min Act: -0.0001

Data Index: 1638854 (Python Code)

Max Activating Token Index: 256

Text #8

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8427. Min Act: -0.0001

Data Index: 1527356 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8597. Min Act: -0.0001

Data Index: 1494967 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.7871. Min Act: -0.0001

Data Index: 1516827 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.5344. Min Act: -0.0001

Data Index: 1515213 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.7005. Min Act: -0.0001

Data Index: 1582446 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8598. Min Act: -0.0001

Data Index: 1447324 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8077. Min Act: -0.0001

Data Index: 1466338 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.6942. Min Act: -0.0001

Data Index: 1451463 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.7251. Min Act: -0.0001

Data Index: 1628649 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.6915. Min Act: -0.0001

Data Index: 1567223 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.7849. Min Act: -0.0001

Data Index: 1653260 (Python Code)

Max Activating Token Index: 351

Text #19

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.6762. Min Act: -0.0001

Data Index: 1497369 (Python Code)

Max Activating Token Index: 543