Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3011 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0098. Min Range: -4.0098
Max Act: 4.0098. Min Act: -0.1700
Data Index: 6776385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 588197 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 974371 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 880502 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 160905 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 811505 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 21218 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 746864 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 996375 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 604071 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 1021850 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 244625 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 218595 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 396164 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 216000 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 1062089 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 194109 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 386181 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 491505 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0098. Min Range: -4.0098
Max Act: 3.9473. Min Act: -0.1700
Data Index: 166545 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19