Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4313 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0040. Min Range: -5.0040
Max Act: 5.0040. Min Act: -0.1700
Data Index: 2059565 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.9415. Min Act: -0.1700
Data Index: 5334005 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.9415. Min Act: -0.1700
Data Index: 1186246 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.9103. Min Act: -0.1700
Data Index: 2800848 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.9103. Min Act: -0.1700
Data Index: 7934375 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8790. Min Act: -0.1700
Data Index: 7035530 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8790. Min Act: -0.1700
Data Index: 6228974 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8478. Min Act: -0.1700
Data Index: 8439531 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8478. Min Act: -0.1700
Data Index: 6349782 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 7588615 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8478. Min Act: -0.1700
Data Index: 8198000 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8478. Min Act: -0.1700
Data Index: 503886 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 4822283 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 447517 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 3984758 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 4561281 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 64051 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 5637066 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 8395582 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0040. Min Range: -5.0040
Max Act: 4.8165. Min Act: -0.1700
Data Index: 4875102 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19