Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.1189. Min Act: -0.1700
Data Index: 2518147 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.1189. Min Act: -0.1700
Data Index: 3802760 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.0876. Min Act: -0.1700
Data Index: 7265282 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.0564. Min Act: -0.1700
Data Index: 1607679 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.0876. Min Act: -0.1700
Data Index: 4734575 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.0564. Min Act: -0.1700
Data Index: 6049165 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.0251. Min Act: -0.1700
Data Index: 6956566 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1189. Min Range: -6.1189
Max Act: 6.0251. Min Act: -0.1700
Data Index: 3351819 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9939. Min Act: -0.1700
Data Index: 112563 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9626. Min Act: -0.1700
Data Index: 5240430 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9626. Min Act: -0.1700
Data Index: 3078637 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9314. Min Act: -0.1700
Data Index: 281248 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9001. Min Act: -0.1700
Data Index: 7115595 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9001. Min Act: -0.1700
Data Index: 4081295 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.9001. Min Act: -0.1700
Data Index: 886522 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.8689. Min Act: -0.1700
Data Index: 438121 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.8689. Min Act: -0.1700
Data Index: 2189866 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.8689. Min Act: -0.1700
Data Index: 6228289 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.8689. Min Act: -0.1700
Data Index: 902509 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1189. Min Range: -6.1189
Max Act: 5.8689. Min Act: -0.1700
Data Index: 1910630 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19