Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0646. Min Range: -6.0646
Max Act: 6.0646. Min Act: -0.1700
Data Index: 5162004 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.8771. Min Act: -0.1700
Data Index: 6424784 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.8771. Min Act: -0.1700
Data Index: 6864285 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.8146. Min Act: -0.1700
Data Index: 2015447 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.7833. Min Act: -0.1700
Data Index: 5939568 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.7521. Min Act: -0.1700
Data Index: 5801353 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6896. Min Act: -0.1700
Data Index: 3214902 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6896. Min Act: -0.1700
Data Index: 3451710 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6896. Min Act: -0.1700
Data Index: 7569084 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6583. Min Act: -0.1700
Data Index: 2979154 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6583. Min Act: -0.1697
Data Index: 8010455 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6271. Min Act: -0.1700
Data Index: 7732764 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.6271. Min Act: -0.1700
Data Index: 7414499 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5958. Min Act: -0.1700
Data Index: 2781593 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5958. Min Act: -0.1700
Data Index: 5785406 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5958. Min Act: -0.1700
Data Index: 7579617 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5958. Min Act: -0.1700
Data Index: 2506666 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5646. Min Act: -0.1700
Data Index: 1051485 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5333. Min Act: -0.1700
Data Index: 456347 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0646. Min Range: -6.0646
Max Act: 5.5646. Min Act: -0.1700
Data Index: 5600758 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19