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

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

Neuron 428 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: 3.9589. Min Range: -3.9589

Max Act: 3.9589. Min Act: -0.1700

Data Index: 1212807 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.9589. Min Act: -0.1700

Data Index: 462411 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.9589. Min Act: -0.1700

Data Index: 466758 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.9589. Min Act: -0.1700

Data Index: 1277451 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.9276. Min Act: -0.1700

Data Index: 438348 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.9276. Min Act: -0.1700

Data Index: 1307208 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.8963. Min Act: -0.1700

Data Index: 524285 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.8963. Min Act: -0.1700

Data Index: 543648 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.8338. Min Act: -0.1700

Data Index: 1046473 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.8651. Min Act: -0.1700

Data Index: 654210 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7712. Min Act: -0.1700

Data Index: 308567 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7712. Min Act: -0.1700

Data Index: 1218920 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7712. Min Act: -0.1700

Data Index: 379314 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7399. Min Act: -0.1700

Data Index: 281887 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1276085 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7712. Min Act: -0.1700

Data Index: 1021304 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7086. Min Act: -0.1700

Data Index: 668828 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7086. Min Act: -0.1700

Data Index: 1074478 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7399. Min Act: -0.1700

Data Index: 609753 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 3.9589. Min Range: -3.9589

Max Act: 3.7086. Min Act: -0.1700

Data Index: 1226743 (C4 (Web Text))

Max Activating Token Index: 615