Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.3472. Min Act: -0.1700
Data Index: 3197063 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2847. Min Act: -0.1700
Data Index: 7081342 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2847. Min Act: -0.1700
Data Index: 6176347 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2847. Min Act: -0.1700
Data Index: 4147792 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2535. Min Act: -0.1700
Data Index: 4937416 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2222. Min Act: -0.1700
Data Index: 6784341 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1910. Min Act: -0.1700
Data Index: 6227325 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2222. Min Act: -0.1700
Data Index: 5209904 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.2222. Min Act: -0.1700
Data Index: 1148097 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1910. Min Act: -0.1700
Data Index: 7487536 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1910. Min Act: -0.1700
Data Index: 5746174 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1597. Min Act: -0.1700
Data Index: 6998461 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1597. Min Act: -0.1700
Data Index: 8327666 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1597. Min Act: -0.1700
Data Index: 5144302 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 842226 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 2845071 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 2216973 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 4969697 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1597. Min Act: -0.1700
Data Index: 85429 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3472. Min Range: -5.3472
Max Act: 5.1285. Min Act: -0.1700
Data Index: 3154824 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19