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

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

Neuron 1021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.9432. Min Act: -0.1700

Data Index: 1340838 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.9432. Min Act: -0.1700

Data Index: 1418036 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8807. Min Act: -0.1700

Data Index: 1595780 (Python Code)

Max Activating Token Index: 627

Text #3

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8494. Min Act: -0.1700

Data Index: 201919 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.8807. Min Act: -0.1700

Data Index: 1502771 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1571472 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1516231 (Python Code)

Max Activating Token Index: 317

Text #7

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1175817 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1493026 (Python Code)

Max Activating Token Index: 588

Text #9

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7243. Min Act: -0.1700

Data Index: 1419682 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7243. Min Act: -0.1699

Data Index: 1583824 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7243. Min Act: -0.1700

Data Index: 1635757 (Python Code)

Max Activating Token Index: 869

Text #12

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.6930. Min Act: -0.1700

Data Index: 164487 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7243. Min Act: -0.1700

Data Index: 639831 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.6930. Min Act: -0.1700

Data Index: 1399938 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.6930. Min Act: -0.1700

Data Index: 1442618 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7243. Min Act: -0.1700

Data Index: 1605410 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.7243. Min Act: -0.1700

Data Index: 1599923 (Python Code)

Max Activating Token Index: 911

Text #18

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.6617. Min Act: -0.1700

Data Index: 1361800 (Python Code)

Max Activating Token Index: 493

Text #19

Max Range: 3.9432. Min Range: -3.9432

Max Act: 3.6930. Min Act: -0.1700

Data Index: 1538070 (Python Code)

Max Activating Token Index: 898