Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.3156. Min Act: -0.1700
Data Index: 4193151 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.2999. Min Act: -0.1700
Data Index: 6585330 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.2528. Min Act: -0.1700
Data Index: 8644118 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.2371. Min Act: -0.1700
Data Index: 6561056 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.2371. Min Act: -0.1700
Data Index: 7200654 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.2057. Min Act: -0.1700
Data Index: 3044193 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1899. Min Act: -0.1700
Data Index: 196217 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1899. Min Act: -0.1700
Data Index: 5853203 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1899. Min Act: -0.1700
Data Index: 1048115 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1899. Min Act: -0.1700
Data Index: 754711 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1899. Min Act: -0.1700
Data Index: 8209061 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1585. Min Act: -0.1700
Data Index: 5331975 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 3894262 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 7956326 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 4193150 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 8823898 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 8282939 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 903897 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1742. Min Act: -0.1700
Data Index: 5389996 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3156. Min Range: -3.3156
Max Act: 3.1585. Min Act: -0.1700
Data Index: 1079821 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19