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

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

Neuron 1743 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4391. Min Act: -0.1700

Data Index: 764719 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4079. Min Act: -0.1700

Data Index: 481558 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3766. Min Act: -0.1700

Data Index: 1197294 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3766. Min Act: -0.1700

Data Index: 245708 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4391. Min Act: -0.1700

Data Index: 1222226 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4391. Min Act: -0.1700

Data Index: 494011 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4391. Min Act: -0.1700

Data Index: 184157 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4079. Min Act: -0.1700

Data Index: 826284 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4391. Min Act: -0.1700

Data Index: 149970 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3766. Min Act: -0.1700

Data Index: 1216841 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3454. Min Act: -0.1700

Data Index: 947599 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.4079. Min Act: -0.1700

Data Index: 664591 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.2516. Min Act: -0.1700

Data Index: 709702 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3454. Min Act: -0.1700

Data Index: 999886 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.2829. Min Act: -0.1700

Data Index: 500809 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3454. Min Act: -0.1700

Data Index: 942545 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3141. Min Act: -0.1700

Data Index: 771188 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3141. Min Act: -0.1700

Data Index: 772508 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3141. Min Act: -0.1700

Data Index: 604228 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 5.4391. Min Range: -5.4391

Max Act: 5.3141. Min Act: -0.1700

Data Index: 899345 (C4 (Web Text))

Max Activating Token Index: 369