Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.7267. Min Act: -0.1700
Data Index: 4645271 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.6954. Min Act: -0.1700
Data Index: 7070479 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.6015. Min Act: -0.1700
Data Index: 6374762 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.5389. Min Act: -0.1700
Data Index: 7835492 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.5076. Min Act: -0.1700
Data Index: 7309898 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4762. Min Act: -0.1700
Data Index: 6563985 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4762. Min Act: -0.1700
Data Index: 3785225 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4762. Min Act: -0.1700
Data Index: 7638462 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4292. Min Act: -0.1700
Data Index: 167467 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4292. Min Act: -0.1700
Data Index: 1448587 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4292. Min Act: -0.1700
Data Index: 1324153 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4136. Min Act: -0.1700
Data Index: 4649558 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3822. Min Act: -0.1700
Data Index: 8608150 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3822. Min Act: -0.1700
Data Index: 6119356 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3979. Min Act: -0.1700
Data Index: 7403691 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3979. Min Act: -0.1700
Data Index: 5501128 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3822. Min Act: -0.1700
Data Index: 5546460 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.4136. Min Act: -0.1700
Data Index: 5895780 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3979. Min Act: -0.1700
Data Index: 6682032 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7267. Min Range: -3.7267
Max Act: 3.3822. Min Act: -0.1700
Data Index: 1773860 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19