Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.7111. Min Act: -0.1700
Data Index: 621167 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.6173. Min Act: -0.1700
Data Index: 5882736 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5861. Min Act: -0.1700
Data Index: 7005700 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5861. Min Act: -0.1700
Data Index: 887167 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5548. Min Act: -0.1700
Data Index: 4594531 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5548. Min Act: -0.1700
Data Index: 7547746 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5548. Min Act: -0.1700
Data Index: 8359233 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5236. Min Act: -0.1700
Data Index: 8721493 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5236. Min Act: -0.1700
Data Index: 812988 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 2612590 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 6712721 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 6204601 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 5199632 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.5236. Min Act: -0.1700
Data Index: 8063539 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 3687344 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 8801343 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4611. Min Act: -0.1700
Data Index: 6612852 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4923. Min Act: -0.1698
Data Index: 635235 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4611. Min Act: -0.1700
Data Index: 3990271 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7111. Min Range: -5.7111
Max Act: 5.4611. Min Act: -0.1700
Data Index: 6446410 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19