Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5227 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.7172. Min Act: -0.1700
Data Index: 2151942 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.6852. Min Act: -0.1700
Data Index: 8035576 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.6692. Min Act: -0.1700
Data Index: 1516897 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.6371. Min Act: -0.1700
Data Index: 6228610 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.6211. Min Act: -0.1700
Data Index: 506870 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.6050. Min Act: -0.1700
Data Index: 3724493 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.6050. Min Act: -0.1700
Data Index: 4423396 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5566. Min Act: -0.1700
Data Index: 7759780 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5728. Min Act: -0.1700
Data Index: 5432729 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5405. Min Act: -0.1700
Data Index: 1846395 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5405. Min Act: -0.1700
Data Index: 7795249 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5081. Min Act: -0.1700
Data Index: 2571206 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5081. Min Act: -0.1700
Data Index: 4652611 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5243. Min Act: -0.1700
Data Index: 7362013 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5081. Min Act: -0.1700
Data Index: 8298971 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5081. Min Act: -0.1700
Data Index: 7616442 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.4919. Min Act: -0.1700
Data Index: 4772269 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.5243. Min Act: -0.1700
Data Index: 3818852 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.4919. Min Act: -0.1700
Data Index: 3447214 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7172. Min Range: -2.7172
Max Act: 2.4919. Min Act: -0.1700
Data Index: 2833479 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19