Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1596 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1867. Min Range: -7.1867
Max Act: 7.1867. Min Act: -0.1700
Data Index: 8721036 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1867. Min Range: -7.1867
Max Act: 7.1867. Min Act: -0.1700
Data Index: 4990877 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1867. Min Range: -7.1867
Max Act: 7.0929. Min Act: -0.1695
Data Index: 2174776 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.9054. Min Act: -0.1700
Data Index: 4659581 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.7804. Min Act: -0.1700
Data Index: 2220847 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.8117. Min Act: -0.1699
Data Index: 1307531 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.8117. Min Act: -0.1700
Data Index: 7290612 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.7804. Min Act: -0.1700
Data Index: 7788147 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.7179. Min Act: -0.1700
Data Index: 2963244 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.5617. Min Act: -0.1700
Data Index: 7720532 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.5617. Min Act: -0.1700
Data Index: 6365264 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.5929. Min Act: -0.1700
Data Index: 29383 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.5304. Min Act: -0.1700
Data Index: 173533 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.4992. Min Act: -0.1700
Data Index: 5749612 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.4992. Min Act: -0.1700
Data Index: 6632864 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.4992. Min Act: -0.1700
Data Index: 7778857 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.4992. Min Act: -0.1700
Data Index: 4036514 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.5304. Min Act: -0.1700
Data Index: 2895175 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.4367. Min Act: -0.1700
Data Index: 5819607 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1867. Min Range: -7.1867
Max Act: 6.4367. Min Act: -0.1700
Data Index: 6832983 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19