Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1118. Min Range: -8.1118
Max Act: 8.1118. Min Act: -0.1700
Data Index: 3016683 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.6743. Min Act: -0.1700
Data Index: 7300915 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.5806. Min Act: -0.1700
Data Index: 5858550 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.6118. Min Act: -0.1700
Data Index: 3958951 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.4243. Min Act: -0.1700
Data Index: 6114918 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.4243. Min Act: -0.1700
Data Index: 5556972 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.3931. Min Act: -0.1700
Data Index: 7987132 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.2993. Min Act: -0.1700
Data Index: 7164093 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.3306. Min Act: -0.1700
Data Index: 6572592 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.2993. Min Act: -0.1700
Data Index: 7986275 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.2681. Min Act: -0.1700
Data Index: 6122362 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.2681. Min Act: -0.1700
Data Index: 8007166 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.2368. Min Act: -0.1700
Data Index: 6106067 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.2368. Min Act: -0.1700
Data Index: 8617304 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 4217691 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 6928074 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 1749059 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 1892039 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.1743. Min Act: -0.1700
Data Index: 4322864 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1118. Min Range: -8.1118
Max Act: 7.1431. Min Act: -0.1700
Data Index: 918769 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19