Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 711 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.4560. Min Act: -0.1700

Data Index: 1407688 (Python Code)

Max Activating Token Index: 228

Text #1

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.4248. Min Act: -0.1700

Data Index: 1628991 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.4248. Min Act: -0.1700

Data Index: 1405116 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.4560. Min Act: -0.1700

Data Index: 1632376 (Python Code)

Max Activating Token Index: 359

Text #4

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.4248. Min Act: -0.1700

Data Index: 1518861 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3623. Min Act: -0.1699

Data Index: 1563201 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3935. Min Act: -0.1700

Data Index: 1527569 (Python Code)

Max Activating Token Index: 677

Text #7

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3935. Min Act: -0.1700

Data Index: 1484246 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3623. Min Act: -0.1700

Data Index: 1581149 (Python Code)

Max Activating Token Index: 614

Text #9

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3935. Min Act: -0.1700

Data Index: 1496318 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.2998. Min Act: -0.1700

Data Index: 1582555 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3310. Min Act: -0.1700

Data Index: 1550352 (Python Code)

Max Activating Token Index: 686

Text #12

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.2998. Min Act: -0.1700

Data Index: 1486122 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3623. Min Act: -0.1700

Data Index: 1550468 (Python Code)

Max Activating Token Index: 561

Text #14

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3623. Min Act: -0.1700

Data Index: 1477741 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3935. Min Act: -0.1700

Data Index: 1555878 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3623. Min Act: -0.1700

Data Index: 1365153 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.4248. Min Act: -0.1700

Data Index: 1471755 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.3310. Min Act: -0.1700

Data Index: 1530815 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 5.4560. Min Range: -5.4560

Max Act: 5.2998. Min Act: -0.1700

Data Index: 1420541 (Python Code)

Max Activating Token Index: 335