Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 603 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1651704 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1516323 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1482249 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1370028 (Python Code)

Max Activating Token Index: 273

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1380046 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1515806 (Python Code)

Max Activating Token Index: 411

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1497340 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1508239 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1631236 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1617961 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0611. Min Act: -0.0003

Data Index: 1512528 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1464414 (Python Code)

Max Activating Token Index: 1001

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1629165 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1439749 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1520820 (Python Code)

Max Activating Token Index: 319

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1450569 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1623854 (Python Code)

Max Activating Token Index: 943

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1440077 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1454377 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1585745 (Python Code)

Max Activating Token Index: 189