Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1867. Min Range: -3.1867
Max Act: 3.1867. Min Act: -0.1700
Data Index: 1918819 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1867. Min Range: -3.1867
Max Act: 3.1552. Min Act: -0.1700
Data Index: 8469610 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1867. Min Range: -3.1867
Max Act: 3.1237. Min Act: -0.1700
Data Index: 5962173 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1867. Min Range: -3.1867
Max Act: 3.0922. Min Act: -0.1700
Data Index: 370494 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1867. Min Range: -3.1867
Max Act: 3.0764. Min Act: -0.1700
Data Index: 1304049 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.9659. Min Act: -0.1700
Data Index: 4919559 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.9659. Min Act: -0.1700
Data Index: 6067734 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.9659. Min Act: -0.1700
Data Index: 5000457 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.9342. Min Act: -0.1700
Data Index: 6889593 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.9184. Min Act: -0.1700
Data Index: 109721 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.9184. Min Act: -0.1700
Data Index: 5452829 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8866. Min Act: -0.1700
Data Index: 762877 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8708. Min Act: -0.1700
Data Index: 8337482 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8390. Min Act: -0.1700
Data Index: 434483 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8390. Min Act: -0.1700
Data Index: 6667080 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8390. Min Act: -0.1700
Data Index: 6496042 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8231. Min Act: -0.1700
Data Index: 1303444 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8231. Min Act: -0.1700
Data Index: 314567 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.8231. Min Act: -0.1700
Data Index: 6054374 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1867. Min Range: -3.1867
Max Act: 2.7913. Min Act: -0.1700
Data Index: 3897627 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19