Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.5080. Min Act: -0.1700
Data Index: 6221363 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.2580. Min Act: -0.1700
Data Index: 8658877 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.2267. Min Act: -0.1700
Data Index: 5919764 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.1955. Min Act: -0.1700
Data Index: 7908938 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.1955. Min Act: -0.1700
Data Index: 669253 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.1642. Min Act: -0.1700
Data Index: 3250276 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.1955. Min Act: -0.1700
Data Index: 2403516 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.1017. Min Act: -0.1700
Data Index: 8468696 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.0705. Min Act: -0.1700
Data Index: 80966 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5080. Min Range: -7.5080
Max Act: 7.0080. Min Act: -0.1700
Data Index: 1953091 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9767. Min Act: -0.1700
Data Index: 5057171 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9767. Min Act: -0.1700
Data Index: 7860277 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9455. Min Act: -0.1700
Data Index: 1538299 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9455. Min Act: -0.1700
Data Index: 2875146 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9455. Min Act: -0.1700
Data Index: 5867273 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9455. Min Act: -0.1700
Data Index: 2384747 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9142. Min Act: -0.1700
Data Index: 8212491 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.9142. Min Act: -0.1700
Data Index: 7514861 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.8830. Min Act: -0.1700
Data Index: 5335710 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5080. Min Range: -7.5080
Max Act: 6.8830. Min Act: -0.1700
Data Index: 3765037 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19