Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1071. Min Range: -5.1071
Max Act: 5.1071. Min Act: -0.1700
Data Index: 791019 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1071. Min Range: -5.1071
Max Act: 5.0446. Min Act: -0.1700
Data Index: 895536 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1071. Min Range: -5.1071
Max Act: 5.0759. Min Act: -0.1700
Data Index: 2145667 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1396946 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1158790 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.8884. Min Act: -0.1700
Data Index: 1344395 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.8571. Min Act: -0.1700
Data Index: 3441123 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.8259. Min Act: -0.1700
Data Index: 8182544 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.8571. Min Act: -0.1700
Data Index: 241006 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.8259. Min Act: -0.1700
Data Index: 5902628 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7946. Min Act: -0.1700
Data Index: 2118240 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7634. Min Act: -0.1700
Data Index: 8218754 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7946. Min Act: -0.1700
Data Index: 6404045 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7634. Min Act: -0.1700
Data Index: 4479024 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7634. Min Act: -0.1700
Data Index: 6772502 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7321. Min Act: -0.1700
Data Index: 5902629 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8011299 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7321. Min Act: -0.1700
Data Index: 5896130 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.7009. Min Act: -0.1700
Data Index: 8432553 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1071. Min Range: -5.1071
Max Act: 4.6696. Min Act: -0.1700
Data Index: 7208033 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19