Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0466. Min Range: -5.0466
Max Act: 5.0466. Min Act: -0.1700
Data Index: 7547358 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.9841. Min Act: -0.1700
Data Index: 6129463 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.9528. Min Act: -0.1700
Data Index: 7247754 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.8903. Min Act: -0.1700
Data Index: 4239299 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.8903. Min Act: -0.1700
Data Index: 3825233 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.8591. Min Act: -0.1700
Data Index: 7595418 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7966. Min Act: -0.1700
Data Index: 3918069 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7966. Min Act: -0.1700
Data Index: 3070504 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7653. Min Act: -0.1700
Data Index: 4749423 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7653. Min Act: -0.1700
Data Index: 8696041 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7653. Min Act: -0.1700
Data Index: 1483626 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7341. Min Act: -0.1700
Data Index: 7774396 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7341. Min Act: -0.1700
Data Index: 3618238 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7028. Min Act: -0.1700
Data Index: 5163093 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7341. Min Act: -0.1700
Data Index: 6590013 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7341. Min Act: -0.1700
Data Index: 3920035 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7341. Min Act: -0.1700
Data Index: 2472286 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7028. Min Act: -0.1700
Data Index: 5176312 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7341. Min Act: -0.1700
Data Index: 2367224 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0466. Min Range: -5.0466
Max Act: 4.7028. Min Act: -0.1700
Data Index: 2668409 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19