Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6175. Min Range: -7.6175
Max Act: 7.6175. Min Act: -0.1700
Data Index: 8563929 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6175. Min Range: -7.6175
Max Act: 7.2425. Min Act: -0.1700
Data Index: 4148778 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6175. Min Range: -7.6175
Max Act: 7.1175. Min Act: -0.1700
Data Index: 7554983 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6175. Min Range: -7.6175
Max Act: 7.1487. Min Act: -0.1700
Data Index: 1551737 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.9925. Min Act: -0.1700
Data Index: 7147463 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.8675. Min Act: -0.1700
Data Index: 6765051 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.8362. Min Act: -0.1700
Data Index: 3068083 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.8675. Min Act: -0.1700
Data Index: 8777201 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.8050. Min Act: -0.1700
Data Index: 7527010 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.8050. Min Act: -0.1700
Data Index: 6928096 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7737. Min Act: -0.1700
Data Index: 6108660 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7737. Min Act: -0.1700
Data Index: 7638135 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7112. Min Act: -0.1700
Data Index: 68614 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7112. Min Act: -0.1700
Data Index: 6824302 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7112. Min Act: -0.1700
Data Index: 3115500 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7112. Min Act: -0.1700
Data Index: 1501403 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.7112. Min Act: -0.1700
Data Index: 8634223 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.6800. Min Act: -0.1700
Data Index: 7188423 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.6800. Min Act: -0.1700
Data Index: 3860755 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6175. Min Range: -7.6175
Max Act: 6.6800. Min Act: -0.1700
Data Index: 3297515 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19