Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4606 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.1687. Min Act: -0.1700
Data Index: 8165150 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.1372. Min Act: -0.1700
Data Index: 2824933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.1057. Min Act: -0.1700
Data Index: 2736291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.1057. Min Act: -0.1700
Data Index: 6474809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 6452351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 1952980 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.1057. Min Act: -0.1700
Data Index: 755622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 6972181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 1222991 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 5433827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 6032233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 2076581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.1057. Min Act: -0.1700
Data Index: 2064955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 7650160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0741. Min Act: -0.1700
Data Index: 8479650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0268. Min Act: -0.1700
Data Index: 6186005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0426. Min Act: -0.1700
Data Index: 5444794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0268. Min Act: -0.1700
Data Index: 5652367 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0426. Min Act: -0.1700
Data Index: 613037 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1687. Min Range: -3.1687
Max Act: 3.0426. Min Act: -0.1700
Data Index: 8189369 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19