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

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

Neuron 660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.7137. Min Act: -0.1700

Data Index: 989467 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6824. Min Act: -0.1700

Data Index: 630031 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6980. Min Act: -0.1700

Data Index: 13212 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6667. Min Act: -0.1700

Data Index: 1316729 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.7137. Min Act: -0.1700

Data Index: 509181 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6824. Min Act: -0.1700

Data Index: 262558 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6354. Min Act: -0.1700

Data Index: 1283555 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6354. Min Act: -0.1700

Data Index: 718819 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5885. Min Act: -0.1700

Data Index: 316894 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6041. Min Act: -0.1700

Data Index: 1317489 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6511. Min Act: -0.1700

Data Index: 1281234 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1358671 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6041. Min Act: -0.1700

Data Index: 667528 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5415. Min Act: -0.1700

Data Index: 638765 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5415. Min Act: -0.1700

Data Index: 346477 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5885. Min Act: -0.1700

Data Index: 201080 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5885. Min Act: -0.1700

Data Index: 58337 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4475. Min Act: -0.1700

Data Index: 158501 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6041. Min Act: -0.1700

Data Index: 791433 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5102. Min Act: -0.1700

Data Index: 226232 (C4 (Web Text))

Max Activating Token Index: 246