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

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

Neuron 1985 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: 5.8070. Min Range: -5.8070

Max Act: 5.8070. Min Act: -0.1700

Data Index: 710461 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.7445. Min Act: -0.1700

Data Index: 503037 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.8070. Min Act: -0.1700

Data Index: 238150 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.7758. Min Act: -0.1700

Data Index: 432858 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6820. Min Act: -0.1700

Data Index: 211821 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6820. Min Act: -0.1700

Data Index: 885328 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6195. Min Act: -0.1700

Data Index: 308073 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6820. Min Act: -0.1700

Data Index: 69201 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6195. Min Act: -0.1700

Data Index: 66027 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6508. Min Act: -0.1700

Data Index: 40877 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6195. Min Act: -0.1700

Data Index: 648805 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6195. Min Act: -0.1700

Data Index: 877819 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.5883. Min Act: -0.1700

Data Index: 1013139 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6508. Min Act: -0.1699

Data Index: 200831 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.6195. Min Act: -0.1700

Data Index: 1011742 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.5258. Min Act: -0.1700

Data Index: 53198 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.5883. Min Act: -0.1700

Data Index: 809499 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.5258. Min Act: -0.1700

Data Index: 55945 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.5570. Min Act: -0.1700

Data Index: 886231 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 5.8070. Min Range: -5.8070

Max Act: 5.5570. Min Act: -0.1700

Data Index: 837997 (C4 (Web Text))

Max Activating Token Index: 789