Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4772 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5126. Min Range: -6.5126
Max Act: 6.5126. Min Act: -0.1700
Data Index: 4099645 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5126. Min Range: -6.5126
Max Act: 6.4813. Min Act: -0.1700
Data Index: 1343902 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5126. Min Range: -6.5126
Max Act: 6.0751. Min Act: -0.1700
Data Index: 4099646 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5126. Min Range: -6.5126
Max Act: 6.0126. Min Act: -0.1700
Data Index: 1343901 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.9813. Min Act: -0.1700
Data Index: 4573880 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.9501. Min Act: -0.1700
Data Index: 4099644 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.9188. Min Act: -0.1700
Data Index: 306964 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.9188. Min Act: -0.1700
Data Index: 572086 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.8876. Min Act: -0.1700
Data Index: 675972 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.8563. Min Act: -0.1700
Data Index: 539405 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.8563. Min Act: -0.1700
Data Index: 3127583 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.8251. Min Act: -0.1700
Data Index: 2592530 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.8251. Min Act: -0.1700
Data Index: 4344293 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7938. Min Act: -0.1700
Data Index: 504986 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1395035 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7658962 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7938. Min Act: -0.1700
Data Index: 8585217 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7626. Min Act: -0.1700
Data Index: 4587262 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7626. Min Act: -0.1700
Data Index: 1018909 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5126. Min Range: -6.5126
Max Act: 5.7001. Min Act: -0.1700
Data Index: 4225371 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19