Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4269 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2265. Min Range: -8.2265
Max Act: 8.2265. Min Act: -0.1700
Data Index: 2578427 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2265. Min Range: -8.2265
Max Act: 8.2265. Min Act: -0.1700
Data Index: 2678170 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.9140. Min Act: -0.1700
Data Index: 2442096 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.9140. Min Act: -0.1700
Data Index: 5600881 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.9140. Min Act: -0.1700
Data Index: 4013903 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.9140. Min Act: -0.1700
Data Index: 957511 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.7265. Min Act: -0.1700
Data Index: 7033616 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.7890. Min Act: -0.1700
Data Index: 8050252 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.7890. Min Act: -0.1700
Data Index: 7815214 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.7890. Min Act: -0.1700
Data Index: 1003327 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.7890. Min Act: -0.1700
Data Index: 3600864 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6015. Min Act: -0.1700
Data Index: 1542026 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6640. Min Act: -0.1700
Data Index: 7366072 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6640. Min Act: -0.1700
Data Index: 2098707 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6640. Min Act: -0.1700
Data Index: 6593423 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6015. Min Act: -0.1700
Data Index: 2308779 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6015. Min Act: -0.1700
Data Index: 2819090 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6015. Min Act: -0.1700
Data Index: 4092510 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.5390. Min Act: -0.1700
Data Index: 397904 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2265. Min Range: -8.2265
Max Act: 7.6015. Min Act: -0.1700
Data Index: 6266522 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19