Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.9925. Min Act: -0.1700
Data Index: 4749433 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.9925. Min Act: -0.1700
Data Index: 2499364 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.9925. Min Act: -0.1700
Data Index: 1245511 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.9613. Min Act: -0.1700
Data Index: 2404299 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.9300. Min Act: -0.1700
Data Index: 8622068 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 1597932 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 5613927 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 8306562 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 857554 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8675. Min Act: -0.1700
Data Index: 4415294 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8363. Min Act: -0.1700
Data Index: 2932781 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8363. Min Act: -0.1700
Data Index: 4538542 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8363. Min Act: -0.1700
Data Index: 6675625 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 1783727 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 7438765 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 1362679 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 4430920 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 2814481 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 5807244 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9925. Min Range: -5.9925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 4676070 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19