Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1145 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.5663. Min Act: -0.1700
Data Index: 7967137 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.3788. Min Act: -0.1700
Data Index: 1660568 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.3163. Min Act: -0.1700
Data Index: 1223909 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.1600. Min Act: -0.1700
Data Index: 234717 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.1913. Min Act: -0.1700
Data Index: 5776076 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.1600. Min Act: -0.1700
Data Index: 5893610 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.0663. Min Act: -0.1700
Data Index: 7249907 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.0663. Min Act: -0.1700
Data Index: 4953921 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.0663. Min Act: -0.1700
Data Index: 3542189 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5663. Min Range: -8.5663
Max Act: 8.0038. Min Act: -0.1700
Data Index: 5889361 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.9100. Min Act: -0.1700
Data Index: 7915060 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.9725. Min Act: -0.1700
Data Index: 227683 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.9100. Min Act: -0.1700
Data Index: 8234442 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.9413. Min Act: -0.1700
Data Index: 4548918 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.8788. Min Act: -0.1700
Data Index: 1120681 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.8475. Min Act: -0.1700
Data Index: 2161388 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.8788. Min Act: -0.1700
Data Index: 3641273 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.8475. Min Act: -0.1700
Data Index: 5334426 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.7850. Min Act: -0.1700
Data Index: 7253695 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5663. Min Range: -8.5663
Max Act: 7.7538. Min Act: -0.1700
Data Index: 3978722 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19