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

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

Neuron 774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1511. Min Range: -3.1511

Max Act: 3.1511. Min Act: -0.1700

Data Index: 1254261 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.1511. Min Range: -3.1511

Max Act: 3.0723. Min Act: -0.1700

Data Index: 134701 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.1511. Min Range: -3.1511

Max Act: 3.0407. Min Act: -0.1700

Data Index: 960631 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 3.1511. Min Range: -3.1511

Max Act: 3.0091. Min Act: -0.1700

Data Index: 649797 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 3.1511. Min Range: -3.1511

Max Act: 3.0091. Min Act: -0.1700

Data Index: 32584 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 3.1511. Min Range: -3.1511

Max Act: 3.0091. Min Act: -0.1700

Data Index: 1256812 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9933. Min Act: -0.1700

Data Index: 403833 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9933. Min Act: -0.1700

Data Index: 1110977 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9933. Min Act: -0.1700

Data Index: 955043 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9775. Min Act: -0.1700

Data Index: 828852 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9933. Min Act: -0.1700

Data Index: 5394 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9775. Min Act: -0.1700

Data Index: 812601 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9616. Min Act: -0.1700

Data Index: 728622 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9616. Min Act: -0.1700

Data Index: 633821 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9616. Min Act: -0.1700

Data Index: 1277153 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9616. Min Act: -0.1700

Data Index: 107980 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9458. Min Act: -0.1700

Data Index: 485042 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9458. Min Act: -0.1700

Data Index: 1175120 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9616. Min Act: -0.1700

Data Index: 272459 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.1511. Min Range: -3.1511

Max Act: 2.9458. Min Act: -0.1700

Data Index: 364570 (C4 (Web Text))

Max Activating Token Index: 708