Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 944 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.7695. Min Act: -0.1700
Data Index: 5079154 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.7070. Min Act: -0.1700
Data Index: 8390556 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5818. Min Act: -0.1700
Data Index: 2806789 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5505. Min Act: -0.1700
Data Index: 8413548 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5191. Min Act: -0.1700
Data Index: 5750775 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5505. Min Act: -0.1700
Data Index: 7182344 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5191. Min Act: -0.1700
Data Index: 4758241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5191. Min Act: -0.1700
Data Index: 7798115 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5191. Min Act: -0.1700
Data Index: 5057126 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.5191. Min Act: -0.1700
Data Index: 5494349 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4878. Min Act: -0.1700
Data Index: 3253796 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4565. Min Act: -0.1700
Data Index: 5375088 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4878. Min Act: -0.1700
Data Index: 5386072 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4878. Min Act: -0.1700
Data Index: 5067627 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4878. Min Act: -0.1700
Data Index: 7952638 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4565. Min Act: -0.1700
Data Index: 5854326 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4251. Min Act: -0.1700
Data Index: 5113862 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4565. Min Act: -0.1700
Data Index: 5078032 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4565. Min Act: -0.1700
Data Index: 3487779 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7695. Min Range: -3.7695
Max Act: 3.4565. Min Act: -0.1700
Data Index: 8281859 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19