Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2083. Min Range: -5.2083
Max Act: 5.2083. Min Act: -0.1700
Data Index: 4326436 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2083. Min Range: -5.2083
Max Act: 5.1458. Min Act: -0.1700
Data Index: 7958401 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2083. Min Range: -5.2083
Max Act: 5.1146. Min Act: -0.1700
Data Index: 8455149 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.9583. Min Act: -0.1700
Data Index: 7958400 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.9583. Min Act: -0.1700
Data Index: 7973248 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.9271. Min Act: -0.1700
Data Index: 1984889 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.9271. Min Act: -0.1700
Data Index: 4728387 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.8646. Min Act: -0.1700
Data Index: 6718057 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.8021. Min Act: -0.1700
Data Index: 7948218 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.8021. Min Act: -0.1700
Data Index: 3086299 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.8021. Min Act: -0.1700
Data Index: 6926857 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.8021. Min Act: -0.1700
Data Index: 353849 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.8021. Min Act: -0.1700
Data Index: 2055443 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7708. Min Act: -0.1700
Data Index: 5052158 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7708. Min Act: -0.1700
Data Index: 5829717 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7708. Min Act: -0.1700
Data Index: 2111977 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7708. Min Act: -0.1700
Data Index: 3221445 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7396. Min Act: -0.1700
Data Index: 651420 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7708. Min Act: -0.1700
Data Index: 6549448 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2083. Min Range: -5.2083
Max Act: 4.7708. Min Act: -0.1700
Data Index: 7628380 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19