Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2106. Min Range: -8.2106
Max Act: 8.2106. Min Act: -0.1700
Data Index: 4254320 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.6168. Min Act: -0.1700
Data Index: 5606720 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.5543. Min Act: -0.1700
Data Index: 3600233 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.5543. Min Act: -0.1700
Data Index: 5455572 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.5231. Min Act: -0.1700
Data Index: 5154456 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.5856. Min Act: -0.1700
Data Index: 4389869 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.5231. Min Act: -0.1700
Data Index: 2821180 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.5543. Min Act: -0.1700
Data Index: 2827738 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.4606. Min Act: -0.1700
Data Index: 290685 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.4606. Min Act: -0.1700
Data Index: 653889 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3668. Min Act: -0.1700
Data Index: 481919 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3668. Min Act: -0.1700
Data Index: 8194433 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3356. Min Act: -0.1700
Data Index: 1257266 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3356. Min Act: -0.1700
Data Index: 8518597 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3356. Min Act: -0.1700
Data Index: 3294314 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3043. Min Act: -0.1700
Data Index: 7856101 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.3043. Min Act: -0.1700
Data Index: 101547 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.2106. Min Act: -0.1700
Data Index: 6025207 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.2106. Min Act: -0.1700
Data Index: 5222090 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2106. Min Range: -8.2106
Max Act: 7.2106. Min Act: -0.1700
Data Index: 2557380 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19