Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4297 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.9455. Min Act: -0.1700
Data Index: 2058044 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0080. Min Range: -8.0080
Max Act: 8.0080. Min Act: -0.1700
Data Index: 509593 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0080. Min Range: -8.0080
Max Act: 8.0080. Min Act: -0.1700
Data Index: 8625652 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.9455. Min Act: -0.1700
Data Index: 2270564 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.8205. Min Act: -0.1700
Data Index: 2968358 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.7580. Min Act: -0.1700
Data Index: 7820946 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.6330. Min Act: -0.1700
Data Index: 1093402 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.6330. Min Act: -0.1700
Data Index: 8069183 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.6330. Min Act: -0.1700
Data Index: 6743625 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.5705. Min Act: -0.1700
Data Index: 4448089 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.5705. Min Act: -0.1700
Data Index: 5023930 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.5705. Min Act: -0.1700
Data Index: 8546762 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.6330. Min Act: -0.1700
Data Index: 6852866 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.4767. Min Act: -0.1700
Data Index: 621952 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.5080. Min Act: -0.1700
Data Index: 7143219 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.5080. Min Act: -0.1700
Data Index: 4385939 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.4767. Min Act: -0.1700
Data Index: 969034 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.4767. Min Act: -0.1700
Data Index: 4905402 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.4767. Min Act: -0.1700
Data Index: 6139026 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0080. Min Range: -8.0080
Max Act: 7.4455. Min Act: -0.1700
Data Index: 2569046 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19