Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4617 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.8157. Min Act: -0.1700
Data Index: 5174433 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.7532. Min Act: -0.1700
Data Index: 5645058 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.7532. Min Act: -0.1700
Data Index: 2276933 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.6907. Min Act: -0.1700
Data Index: 937241 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.6907. Min Act: -0.1700
Data Index: 6880520 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.5032. Min Act: -0.1700
Data Index: 6806415 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.5032. Min Act: -0.1700
Data Index: 3882959 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.5032. Min Act: -0.1700
Data Index: 6938838 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.5032. Min Act: -0.1700
Data Index: 3849692 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.5032. Min Act: -0.1700
Data Index: 3145877 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.4407. Min Act: -0.1700
Data Index: 6540739 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 551214 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 4081005 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.4407. Min Act: -0.1700
Data Index: 2909673 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 747098 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.4407. Min Act: -0.1700
Data Index: 818065 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 4412425 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 4429585 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 2753425 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8157. Min Range: -10.8157
Max Act: 10.3782. Min Act: -0.1700
Data Index: 4809768 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19