Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0198. Min Range: -8.0198
Max Act: 8.0198. Min Act: -0.1700
Data Index: 6832303 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.8948. Min Act: -0.1700
Data Index: 6588590 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.8948. Min Act: -0.1700
Data Index: 556953 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.8323. Min Act: -0.1700
Data Index: 6620814 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.8323. Min Act: -0.1700
Data Index: 72004 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7698. Min Act: -0.1700
Data Index: 6197130 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7698. Min Act: -0.1700
Data Index: 957854 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7698. Min Act: -0.1700
Data Index: 957859 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7698. Min Act: -0.1700
Data Index: 8279303 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7698. Min Act: -0.1700
Data Index: 679995 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7073. Min Act: -0.1700
Data Index: 6598891 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7073. Min Act: -0.1700
Data Index: 7850842 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.7073. Min Act: -0.1700
Data Index: 1065871 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6761. Min Act: -0.1700
Data Index: 7591648 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6761. Min Act: -0.1700
Data Index: 1202151 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6448. Min Act: -0.1700
Data Index: 8358070 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6448. Min Act: -0.1700
Data Index: 8816363 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6448. Min Act: -0.1700
Data Index: 435394 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6448. Min Act: -0.1700
Data Index: 2354003 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0198. Min Range: -8.0198
Max Act: 7.6448. Min Act: -0.1700
Data Index: 3060411 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19