Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5780 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.1779. Min Act: -0.1700
Data Index: 5018755 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0529. Min Act: -0.1700
Data Index: 122023 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0529. Min Act: -0.1700
Data Index: 4598768 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0529. Min Act: -0.1700
Data Index: 5559629 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0529. Min Act: -0.1700
Data Index: 8530975 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0529. Min Act: -0.1700
Data Index: 4598769 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0217. Min Act: -0.1700
Data Index: 7710935 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1779. Min Range: -5.1779
Max Act: 5.0217. Min Act: -0.1700
Data Index: 7005935 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9904. Min Act: -0.1700
Data Index: 4598781 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9592. Min Act: -0.1700
Data Index: 1003586 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9904. Min Act: -0.1700
Data Index: 856239 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9592. Min Act: -0.1700
Data Index: 1003582 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9592. Min Act: -0.1700
Data Index: 1530373 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9279. Min Act: -0.1700
Data Index: 1995253 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9592. Min Act: -0.1700
Data Index: 667762 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9592. Min Act: -0.1700
Data Index: 3020430 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9592. Min Act: -0.1700
Data Index: 122019 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9279. Min Act: -0.1700
Data Index: 7178786 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9279. Min Act: -0.1700
Data Index: 122028 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1779. Min Range: -5.1779
Max Act: 4.9279. Min Act: -0.1700
Data Index: 3020427 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19