Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5796 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2175. Min Range: -5.2175
Max Act: 5.2175. Min Act: -0.1700
Data Index: 755634 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2175. Min Range: -5.2175
Max Act: 5.0613. Min Act: -0.1700
Data Index: 5621410 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.9675. Min Act: -0.1700
Data Index: 5159596 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.9675. Min Act: -0.1700
Data Index: 6200598 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.9675. Min Act: -0.1700
Data Index: 5103674 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.9363. Min Act: -0.1700
Data Index: 4257515 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5547012 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.8425. Min Act: -0.1700
Data Index: 8227160 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.8738. Min Act: -0.1700
Data Index: 3980683 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.8113. Min Act: -0.1700
Data Index: 8017937 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7800. Min Act: -0.1700
Data Index: 7140859 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7800. Min Act: -0.1700
Data Index: 7529555 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7800. Min Act: -0.1700
Data Index: 5831692 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7488. Min Act: -0.1700
Data Index: 5427976 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7488. Min Act: -0.1700
Data Index: 1813954 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7488. Min Act: -0.1700
Data Index: 7902892 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7488. Min Act: -0.1700
Data Index: 152572 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7175. Min Act: -0.1700
Data Index: 7682787 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7488. Min Act: -0.1700
Data Index: 5447495 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2175. Min Range: -5.2175
Max Act: 4.7175. Min Act: -0.1700
Data Index: 8026378 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19