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

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

Neuron 1364 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2843. Min Range: -5.2843

Max Act: 5.2843. Min Act: -0.1700

Data Index: 343541 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 5.2843. Min Range: -5.2843

Max Act: 5.1280. Min Act: -0.1700

Data Index: 174926 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 5.2843. Min Range: -5.2843

Max Act: 5.0968. Min Act: -0.1700

Data Index: 277104 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 5.2843. Min Range: -5.2843

Max Act: 5.0968. Min Act: -0.1700

Data Index: 1320321 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 5.2843. Min Range: -5.2843

Max Act: 5.0343. Min Act: -0.1700

Data Index: 1311668 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.9718. Min Act: -0.1700

Data Index: 554148 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8780. Min Act: -0.1700

Data Index: 1366465 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8468. Min Act: -0.1700

Data Index: 253207 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.9093. Min Act: -0.1700

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8468. Min Act: -0.1700

Data Index: 1353716 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.9093. Min Act: -0.1700

Data Index: 94955 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8780. Min Act: -0.1700

Data Index: 1062392 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8780. Min Act: -0.1700

Data Index: 164805 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8780. Min Act: -0.1700

Data Index: 299418 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8468. Min Act: -0.1700

Data Index: 570913 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8468. Min Act: -0.1700

Data Index: 407299 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.8312. Min Act: -0.1700

Data Index: 316545 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.7999. Min Act: -0.1700

Data Index: 1256971 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.7374. Min Act: -0.1700

Data Index: 824697 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 5.2843. Min Range: -5.2843

Max Act: 4.7686. Min Act: -0.1700

Data Index: 1075408 (C4 (Web Text))

Max Activating Token Index: 795