Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2248 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.5222. Min Act: -0.1700
Data Index: 7258932 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.4597. Min Act: -0.1700
Data Index: 1770158 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3972. Min Act: -0.1700
Data Index: 8058550 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3035. Min Act: -0.1700
Data Index: 7207958 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3347. Min Act: -0.1700
Data Index: 2227390 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1785. Min Act: -0.1700
Data Index: 6252436 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1160. Min Act: -0.1700
Data Index: 5602643 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1160. Min Act: -0.1700
Data Index: 3433312 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.0847. Min Act: -0.1700
Data Index: 4673899 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.0535. Min Act: -0.1700
Data Index: 2053541 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.0222. Min Act: -0.1700
Data Index: 8071107 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.0535. Min Act: -0.1700
Data Index: 8340770 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.0222. Min Act: -0.1700
Data Index: 7606301 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9910. Min Act: -0.1700
Data Index: 4735970 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9910. Min Act: -0.1700
Data Index: 6859808 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9910. Min Act: -0.1700
Data Index: 3089689 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9597. Min Act: -0.1700
Data Index: 4798761 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9910. Min Act: -0.1700
Data Index: 826099 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9597. Min Act: -0.1700
Data Index: 8340772 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9285. Min Act: -0.1700
Data Index: 4941011 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19