Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0066. Min Range: -4.0066
Max Act: 4.0066. Min Act: -0.1700
Data Index: 8625095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0066. Min Range: -4.0066
Max Act: 4.0066. Min Act: -0.1700
Data Index: 4349623 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9753. Min Act: -0.1700
Data Index: 5732001 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9753. Min Act: -0.1700
Data Index: 3183905 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9753. Min Act: -0.1700
Data Index: 5191144 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9753. Min Act: -0.1700
Data Index: 4227580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 1393231 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 5615703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 2293546 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 5539361 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 8521773 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 3597380 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 8364124 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 7957250 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 6106167 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 5862347 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9441. Min Act: -0.1700
Data Index: 3146807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9128. Min Act: -0.1700
Data Index: 2250664 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9128. Min Act: -0.1700
Data Index: 278332 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0066. Min Range: -4.0066
Max Act: 3.9128. Min Act: -0.1700
Data Index: 5567668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19