Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1204. Min Range: -7.1204
Max Act: 7.1204. Min Act: -0.1700
Data Index: 7067863 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.9954. Min Act: -0.1700
Data Index: 2104662 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.9017. Min Act: -0.1700
Data Index: 1730677 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.8079. Min Act: -0.1700
Data Index: 3302018 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.8079. Min Act: -0.1700
Data Index: 716977 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.8079. Min Act: -0.1700
Data Index: 5330209 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.8079. Min Act: -0.1700
Data Index: 6954596 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.7454. Min Act: -0.1700
Data Index: 7180908 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.7142. Min Act: -0.1700
Data Index: 7067850 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.7454. Min Act: -0.1700
Data Index: 37519 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.7142. Min Act: -0.1700
Data Index: 4853241 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.7454. Min Act: -0.1700
Data Index: 8098597 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6829. Min Act: -0.1700
Data Index: 2623541 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6829. Min Act: -0.1700
Data Index: 7880880 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.7142. Min Act: -0.1700
Data Index: 1586852 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6829. Min Act: -0.1700
Data Index: 1960169 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6517. Min Act: -0.1700
Data Index: 8526206 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6517. Min Act: -0.1700
Data Index: 8205507 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6204. Min Act: -0.1700
Data Index: 7359510 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1204. Min Range: -7.1204
Max Act: 6.6204. Min Act: -0.1700
Data Index: 4823860 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19