Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0035. Min Range: -6.0035
Max Act: 6.0035. Min Act: -0.1700
Data Index: 7245523 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0035. Min Range: -6.0035
Max Act: 6.0035. Min Act: -0.1700
Data Index: 5875922 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.9723. Min Act: -0.1700
Data Index: 264519 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.8160. Min Act: -0.1700
Data Index: 4702564 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.8473. Min Act: -0.1700
Data Index: 5998437 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.8473. Min Act: -0.1700
Data Index: 1849197 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.8160. Min Act: -0.1700
Data Index: 735605 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.8160. Min Act: -0.1700
Data Index: 1004528 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.7848. Min Act: -0.1700
Data Index: 8095035 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.7848. Min Act: -0.1700
Data Index: 8071563 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.7223. Min Act: -0.1700
Data Index: 4190694 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.7223. Min Act: -0.1700
Data Index: 7798961 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6910. Min Act: -0.1700
Data Index: 8051133 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6598. Min Act: -0.1700
Data Index: 8435870 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6598. Min Act: -0.1700
Data Index: 8697910 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6910. Min Act: -0.1700
Data Index: 3064740 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6598. Min Act: -0.1700
Data Index: 5523098 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6598. Min Act: -0.1700
Data Index: 3922069 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6598. Min Act: -0.1700
Data Index: 7145216 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0035. Min Range: -6.0035
Max Act: 5.6285. Min Act: -0.1700
Data Index: 3833509 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19