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

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

Neuron 1915 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: 5.9673. Min Range: -5.9673

Max Act: 5.9048. Min Act: -0.1700

Data Index: 853390 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.8423. Min Act: -0.1700

Data Index: 600411 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.9673. Min Act: -0.1700

Data Index: 271273 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.6861. Min Act: -0.1700

Data Index: 1061567 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.7486. Min Act: -0.1700

Data Index: 1114170 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.5923. Min Act: -0.1700

Data Index: 1206637 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.5923. Min Act: -0.1700

Data Index: 626957 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4673. Min Act: -0.1700

Data Index: 969518 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.3736. Min Act: -0.1700

Data Index: 1164518 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4986. Min Act: -0.1700

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4986. Min Act: -0.1700

Data Index: 557654 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4673. Min Act: -0.1700

Data Index: 183865 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4048. Min Act: -0.1700

Data Index: 624592 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4986. Min Act: -0.1700

Data Index: 182209 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.2798. Min Act: -0.1700

Data Index: 915078 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.2798. Min Act: -0.1700

Data Index: 1245788 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.4361. Min Act: -0.1700

Data Index: 224524 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.2486. Min Act: -0.1700

Data Index: 1290950 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.2486. Min Act: -0.1700

Data Index: 35391 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 5.9673. Min Range: -5.9673

Max Act: 5.1548. Min Act: -0.1700

Data Index: 635833 (C4 (Web Text))

Max Activating Token Index: 110