Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1498. Min Range: -2.1498

Max Act: 2.1498. Min Act: -0.0000

Data Index: 1503648 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1596556 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1601938 (Python Code)

Max Activating Token Index: 509

Text #3

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7541. Min Act: -0.0000

Data Index: 835456 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1488421 (Python Code)

Max Activating Token Index: 481

Text #5

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1476772 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7286. Min Act: -0.0000

Data Index: 1439097 (Python Code)

Max Activating Token Index: 958

Text #7

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7113. Min Act: -0.0000

Data Index: 1482165 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.7857. Min Act: -0.0000

Data Index: 1413102 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1459174 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1512877 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.5053. Min Act: -0.0000

Data Index: 1507352 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1535454 (Python Code)

Max Activating Token Index: 225

Text #13

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1542662 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1482815 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.5670. Min Act: -0.0000

Data Index: 1380385 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1410611 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1180575 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1422383 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 2.1498. Min Range: -2.1498

Max Act: 1.4837. Min Act: -0.0000

Data Index: 1015999 (C4 (Web Text))

Max Activating Token Index: 848