Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.3068. Min Act: -0.1700
Data Index: 7922386 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.2756. Min Act: -0.1700
Data Index: 4204421 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.1505. Min Act: -0.1700
Data Index: 8225037 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.1505. Min Act: -0.1700
Data Index: 6220966 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.1193. Min Act: -0.1700
Data Index: 6469758 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.1193. Min Act: -0.1700
Data Index: 4740678 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.0568. Min Act: -0.1700
Data Index: 5564976 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.0255. Min Act: -0.1700
Data Index: 7349515 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3068. Min Range: -4.3068
Max Act: 4.0255. Min Act: -0.1700
Data Index: 369781 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.9943. Min Act: -0.1700
Data Index: 5242462 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.9317. Min Act: -0.1700
Data Index: 2220398 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.9317. Min Act: -0.1700
Data Index: 3790885 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8692. Min Act: -0.1700
Data Index: 6874558 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8379. Min Act: -0.1700
Data Index: 3900961 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8379. Min Act: -0.1700
Data Index: 266109 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4878023 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8067. Min Act: -0.1700
Data Index: 8224113 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8067. Min Act: -0.1700
Data Index: 7062769 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8067. Min Act: -0.1700
Data Index: 3641725 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3068. Min Range: -4.3068
Max Act: 3.8067. Min Act: -0.1700
Data Index: 8594191 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19