Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1250. Min Range: -6.1250
Max Act: 6.1250. Min Act: -0.1700
Data Index: 2808752 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1250. Min Range: -6.1250
Max Act: 6.0625. Min Act: -0.1700
Data Index: 2681975 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2540166 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.8438. Min Act: -0.1700
Data Index: 6994784 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.8125. Min Act: -0.1700
Data Index: 1373098 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.8438. Min Act: -0.1700
Data Index: 1575583 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.8125. Min Act: -0.1700
Data Index: 4402526 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.8125. Min Act: -0.1700
Data Index: 8402135 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.8125. Min Act: -0.1700
Data Index: 5144151 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7500. Min Act: -0.1700
Data Index: 8493148 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7500. Min Act: -0.1700
Data Index: 1963962 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7500. Min Act: -0.1700
Data Index: 7253857 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7813. Min Act: -0.1700
Data Index: 4220122 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7500. Min Act: -0.1700
Data Index: 4975302 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4220125 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7188. Min Act: -0.1700
Data Index: 2587051 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7188. Min Act: -0.1700
Data Index: 2039326 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7188. Min Act: -0.1700
Data Index: 297649 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7188. Min Act: -0.1700
Data Index: 1506847 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1250. Min Range: -6.1250
Max Act: 5.7188. Min Act: -0.1700
Data Index: 681095 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19