Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.4937. Min Act: -0.1700
Data Index: 5036960 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.2750. Min Act: -0.1700
Data Index: 5518066 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.3062. Min Act: -0.1700
Data Index: 5641923 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.2437. Min Act: -0.1700
Data Index: 5440574 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.2125. Min Act: -0.1700
Data Index: 5518065 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1500. Min Act: -0.1700
Data Index: 2470236 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1187. Min Act: -0.1700
Data Index: 8303217 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1500. Min Act: -0.1700
Data Index: 6296068 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1500. Min Act: -0.1700
Data Index: 8699283 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1812. Min Act: -0.1700
Data Index: 1752769 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1187. Min Act: -0.1700
Data Index: 5314080 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1187. Min Act: -0.1700
Data Index: 3669763 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.0875. Min Act: -0.1700
Data Index: 2691252 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.1187. Min Act: -0.1700
Data Index: 263489 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.0875. Min Act: -0.1700
Data Index: 6257112 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4937. Min Range: -6.4937
Max Act: 6.0250. Min Act: -0.1700
Data Index: 8404204 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4937. Min Range: -6.4937
Max Act: 5.9937. Min Act: -0.1700
Data Index: 907780 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4937. Min Range: -6.4937
Max Act: 5.9312. Min Act: -0.1700
Data Index: 6024103 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4937. Min Range: -6.4937
Max Act: 5.9625. Min Act: -0.1700
Data Index: 7955673 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4937. Min Range: -6.4937
Max Act: 5.9312. Min Act: -0.1700
Data Index: 2825749 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19