Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1168 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.7876. Min Act: -0.1700
Data Index: 525911 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.7876. Min Act: -0.1700
Data Index: 2813654 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.7564. Min Act: -0.1700
Data Index: 449098 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.7251. Min Act: -0.1700
Data Index: 3511190 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6626. Min Act: -0.1700
Data Index: 2696986 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6939. Min Act: -0.1700
Data Index: 8293251 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6314. Min Act: -0.1700
Data Index: 6919943 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6314. Min Act: -0.1700
Data Index: 525912 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6314. Min Act: -0.1700
Data Index: 1633258 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6314. Min Act: -0.1700
Data Index: 2550328 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6001. Min Act: -0.1700
Data Index: 4310071 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6001. Min Act: -0.1700
Data Index: 7083780 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.6001. Min Act: -0.1700
Data Index: 7577716 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5689. Min Act: -0.1700
Data Index: 5925276 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5064. Min Act: -0.1700
Data Index: 69824 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5376. Min Act: -0.1700
Data Index: 2027257 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5064. Min Act: -0.1700
Data Index: 3511191 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5064. Min Act: -0.1700
Data Index: 1518996 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5064. Min Act: -0.1700
Data Index: 6596662 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7876. Min Range: -6.7876
Max Act: 6.5064. Min Act: -0.1700
Data Index: 7342662 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19