Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.2002. Min Act: -0.1700
Data Index: 8190581 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2002. Min Range: -5.2002
Max Act: 5.0127. Min Act: -0.1700
Data Index: 2968954 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9502. Min Act: -0.1700
Data Index: 3458136 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9502. Min Act: -0.1700
Data Index: 2201613 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9189. Min Act: -0.1700
Data Index: 2584566 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9189. Min Act: -0.1700
Data Index: 4538811 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.9189. Min Act: -0.1700
Data Index: 1849613 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8877. Min Act: -0.1700
Data Index: 1182264 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 6818191 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8564. Min Act: -0.1700
Data Index: 5372028 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8564. Min Act: -0.1700
Data Index: 3413044 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 1489860 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 7366790 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 3630197 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.7939. Min Act: -0.1700
Data Index: 3546525 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 5442823 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 950806 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.7939. Min Act: -0.1700
Data Index: 8519130 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.8252. Min Act: -0.1700
Data Index: 6305658 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2002. Min Range: -5.2002
Max Act: 4.7939. Min Act: -0.1700
Data Index: 1367603 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19