Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.1504. Min Act: -0.1700
Data Index: 1367949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.1504. Min Act: -0.1700
Data Index: 4054375 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.1189. Min Act: -0.1700
Data Index: 5912980 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.1031. Min Act: -0.1700
Data Index: 1015875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.1031. Min Act: -0.1700
Data Index: 546570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0873. Min Act: -0.1700
Data Index: 526110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0873. Min Act: -0.1700
Data Index: 5430106 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 7920132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 8063905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 2086934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 78935 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 7728446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 7703672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0716. Min Act: -0.1700
Data Index: 7216190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0558. Min Act: -0.1700
Data Index: 7793771 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0558. Min Act: -0.1700
Data Index: 8187829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0558. Min Act: -0.1700
Data Index: 8587228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0558. Min Act: -0.1700
Data Index: 5719964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0558. Min Act: -0.1700
Data Index: 320174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1504. Min Range: -3.1504
Max Act: 3.0558. Min Act: -0.1700
Data Index: 6489360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19