Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.5259. Min Act: -0.1700
Data Index: 4616952 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.4634. Min Act: -0.1700
Data Index: 5495880 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.1821. Min Act: -0.1700
Data Index: 2833151 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.0571. Min Act: -0.1700
Data Index: 3942863 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9946. Min Act: -0.1700
Data Index: 926669 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9634. Min Act: -0.1700
Data Index: 5781274 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9009. Min Act: -0.1700
Data Index: 6880434 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 1282983 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.8071. Min Act: -0.1700
Data Index: 8518249 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.8071. Min Act: -0.1700
Data Index: 5651188 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.7134. Min Act: -0.1700
Data Index: 2280048 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6821. Min Act: -0.1700
Data Index: 1771077 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6821. Min Act: -0.1700
Data Index: 2723514 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6196. Min Act: -0.1700
Data Index: 1666129 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6509. Min Act: -0.1700
Data Index: 7335495 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6509. Min Act: -0.1700
Data Index: 3300412 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6196. Min Act: -0.1700
Data Index: 4234321 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6509. Min Act: -0.1700
Data Index: 3676697 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.6509. Min Act: -0.1700
Data Index: 3673925 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.5884. Min Act: -0.1700
Data Index: 3234786 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19