Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.6125. Min Act: -0.1700
Data Index: 7919243 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.3938. Min Act: -0.1700
Data Index: 2818968 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.3938. Min Act: -0.1700
Data Index: 2907955 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.3625. Min Act: -0.1700
Data Index: 1128785 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4677651 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.2375. Min Act: -0.1700
Data Index: 5745916 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.2063. Min Act: -0.1700
Data Index: 6922385 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.2063. Min Act: -0.1700
Data Index: 4000460 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.2375. Min Act: -0.1700
Data Index: 186633 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1750. Min Act: -0.1700
Data Index: 7292879 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1438. Min Act: -0.1700
Data Index: 7202671 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1438. Min Act: -0.1700
Data Index: 6847332 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1438. Min Act: -0.1700
Data Index: 2016442 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1750. Min Act: -0.1700
Data Index: 102178 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1125. Min Act: -0.1700
Data Index: 679508 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.1125. Min Act: -0.1700
Data Index: 7281699 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.0813. Min Act: -0.1700
Data Index: 1002997 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.0500. Min Act: -0.1700
Data Index: 8666301 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.0500. Min Act: -0.1700
Data Index: 7379058 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6125. Min Range: -5.6125
Max Act: 5.0188. Min Act: -0.1700
Data Index: 7885728 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19