Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 575 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.2224. Min Act: -0.1700
Data Index: 6682269 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.1910. Min Act: -0.1700
Data Index: 2471169 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.2067. Min Act: -0.1700
Data Index: 1433163 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.1752. Min Act: -0.1700
Data Index: 6894334 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.1752. Min Act: -0.1700
Data Index: 8267434 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.1280. Min Act: -0.1700
Data Index: 7755227 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0965. Min Act: -0.1700
Data Index: 1972313 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0807. Min Act: -0.1700
Data Index: 5384171 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0649. Min Act: -0.1700
Data Index: 7569445 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0492. Min Act: -0.1700
Data Index: 4758256 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0492. Min Act: -0.1700
Data Index: 3720412 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0492. Min Act: -0.1700
Data Index: 1063557 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0492. Min Act: -0.1700
Data Index: 4645262 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0492. Min Act: -0.1700
Data Index: 6296160 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0492. Min Act: -0.1700
Data Index: 8515019 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0334. Min Act: -0.1700
Data Index: 7914347 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0334. Min Act: -0.1700
Data Index: 291785 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0018. Min Act: -0.1700
Data Index: 3122007 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2224. Min Range: -3.2224
Max Act: 2.9860. Min Act: -0.1700
Data Index: 7569444 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2224. Min Range: -3.2224
Max Act: 3.0018. Min Act: -0.1700
Data Index: 8796860 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19