Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 525 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.8014. Min Act: -0.1700

Data Index: 436343 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.5514. Min Act: -0.1700

Data Index: 200594 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.4889. Min Act: -0.1700

Data Index: 673779 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.4577. Min Act: -0.1700

Data Index: 436852 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.4264. Min Act: -0.1700

Data Index: 536616 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3952. Min Act: -0.1700

Data Index: 1345085 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3639. Min Act: -0.1700

Data Index: 972090 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3639. Min Act: -0.1700

Data Index: 391907 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.4264. Min Act: -0.1700

Data Index: 1253944 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.2702. Min Act: -0.1700

Data Index: 67714 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3014. Min Act: -0.1700

Data Index: 209376 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3639. Min Act: -0.1700

Data Index: 889647 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3327. Min Act: -0.1700

Data Index: 369674 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.2702. Min Act: -0.1700

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3014. Min Act: -0.1700

Data Index: 681206 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3327. Min Act: -0.1700

Data Index: 1118739 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3014. Min Act: -0.1700

Data Index: 722184 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.2077. Min Act: -0.1700

Data Index: 902097 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.2702. Min Act: -0.1700

Data Index: 59536 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 5.8014. Min Range: -5.8014

Max Act: 5.3014. Min Act: -0.1700

Data Index: 949136 (C4 (Web Text))

Max Activating Token Index: 493