Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9687. Min Act: -0.1700
Data Index: 7403070 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9687. Min Act: -0.1700
Data Index: 7258523 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9687. Min Act: -0.1700
Data Index: 8476555 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9374. Min Act: -0.1700
Data Index: 1566243 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9374. Min Act: -0.1700
Data Index: 1079960 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9062. Min Act: -0.1700
Data Index: 3328919 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9374. Min Act: -0.1700
Data Index: 8236734 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.9062. Min Act: -0.1700
Data Index: 1688454 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8437. Min Act: -0.1700
Data Index: 6748161 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8437. Min Act: -0.1700
Data Index: 1969082 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8437. Min Act: -0.1700
Data Index: 8236736 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8437. Min Act: -0.1700
Data Index: 706455 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8437. Min Act: -0.1700
Data Index: 8298608 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8124. Min Act: -0.1700
Data Index: 2034104 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.8124. Min Act: -0.1700
Data Index: 6283136 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.7812. Min Act: -0.1700
Data Index: 8297200 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.7812. Min Act: -0.1700
Data Index: 4210878 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.7812. Min Act: -0.1700
Data Index: 2526041 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.7812. Min Act: -0.1700
Data Index: 5894428 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9687. Min Range: -5.9687
Max Act: 5.7812. Min Act: -0.1700
Data Index: 326193 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19