Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 786 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.6446. Min Act: -0.1700

Data Index: 1380233 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1601918 (Python Code)

Max Activating Token Index: 948

Text #2

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1406634 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1479568 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3939. Min Act: -0.1700

Data Index: 1362467 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1456025 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1570228 (Python Code)

Max Activating Token Index: 453

Text #7

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1573208 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1427153 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1586084 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3625. Min Act: -0.1700

Data Index: 1650203 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1394540 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2997. Min Act: -0.1700

Data Index: 1533879 (Python Code)

Max Activating Token Index: 1015

Text #13

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1645823 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2683. Min Act: -0.1700

Data Index: 1515618 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2997. Min Act: -0.1698

Data Index: 1596794 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2997. Min Act: -0.1700

Data Index: 1562974 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2683. Min Act: -0.1700

Data Index: 1518522 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2997. Min Act: -0.1700

Data Index: 1567863 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 3.6446. Min Range: -3.6446

Max Act: 3.2997. Min Act: -0.1700

Data Index: 1397231 (Python Code)

Max Activating Token Index: 455