Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.6063. Min Act: -0.1700
Data Index: 1356008 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.5438. Min Act: -0.1700
Data Index: 6613098 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.4813. Min Act: -0.1700
Data Index: 6613092 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.3250. Min Act: -0.1700
Data Index: 2738447 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.3250. Min Act: -0.1700
Data Index: 7289871 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.2938. Min Act: -0.1700
Data Index: 65952 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.2938. Min Act: -0.1700
Data Index: 2934794 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.2313. Min Act: -0.1700
Data Index: 2876744 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.2313. Min Act: -0.1700
Data Index: 2876745 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1688. Min Act: -0.1700
Data Index: 4093899 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1688. Min Act: -0.1700
Data Index: 3208282 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1688. Min Act: -0.1700
Data Index: 2313551 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1688. Min Act: -0.1700
Data Index: 5066796 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1375. Min Act: -0.1700
Data Index: 283464 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1375. Min Act: -0.1700
Data Index: 1247561 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1375. Min Act: -0.1700
Data Index: 7289873 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1063. Min Act: -0.1700
Data Index: 222110 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1063. Min Act: -0.1700
Data Index: 3655427 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1375. Min Act: -0.1700
Data Index: 5398251 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6063. Min Range: -6.6063
Max Act: 6.1063. Min Act: -0.1700
Data Index: 7238159 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19