Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 472 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.5252. Min Act: -0.1700
Data Index: 4877251 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4627. Min Act: -0.1700
Data Index: 5596799 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4627. Min Act: -0.1700
Data Index: 6978709 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4627. Min Act: -0.1700
Data Index: 2724543 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4940. Min Act: -0.1700
Data Index: 5763219 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4315. Min Act: -0.1700
Data Index: 4721149 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4002. Min Act: -0.1700
Data Index: 3218684 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4002. Min Act: -0.1700
Data Index: 5184215 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3690. Min Act: -0.1700
Data Index: 3185953 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.4002. Min Act: -0.1700
Data Index: 6462532 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3690. Min Act: -0.1700
Data Index: 1107896 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3690. Min Act: -0.1700
Data Index: 3784652 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3377. Min Act: -0.1700
Data Index: 7960568 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3690. Min Act: -0.1700
Data Index: 7233500 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3690. Min Act: -0.1700
Data Index: 5777240 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3065. Min Act: -0.1695
Data Index: 7575434 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3377. Min Act: -0.1700
Data Index: 7530091 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3377. Min Act: -0.1700
Data Index: 3922299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3377. Min Act: -0.1700
Data Index: 1150764 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5252. Min Range: -6.5252
Max Act: 6.3377. Min Act: -0.1700
Data Index: 5170839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19