Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.4404. Min Act: -0.1700
Data Index: 5163562 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.2529. Min Act: -0.1700
Data Index: 7653508 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.2529. Min Act: -0.1700
Data Index: 2368805 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.2217. Min Act: -0.1700
Data Index: 2151451 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.2217. Min Act: -0.1700
Data Index: 1441833 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1904. Min Act: -0.1700
Data Index: 3381608 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1904. Min Act: -0.1700
Data Index: 1633701 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.2217. Min Act: -0.1700
Data Index: 5731959 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 7503869 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5802173 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5793159 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5695770 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 2114794 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 4049555 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 8243994 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 429134 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1592. Min Act: -0.1700
Data Index: 1605837 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1279. Min Act: -0.1700
Data Index: 8660699 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.1279. Min Act: -0.1700
Data Index: 7533981 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4404. Min Range: -5.4404
Max Act: 5.0967. Min Act: -0.1700
Data Index: 578838 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19