Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.6999. Min Act: -0.1700
Data Index: 7269004 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.4811. Min Act: -0.1700
Data Index: 53934 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.3874. Min Act: -0.1700
Data Index: 6547652 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.3249. Min Act: -0.1700
Data Index: 8223330 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.3249. Min Act: -0.1700
Data Index: 1155763 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.2624. Min Act: -0.1700
Data Index: 6105029 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.2624. Min Act: -0.1700
Data Index: 4595276 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.2311. Min Act: -0.1700
Data Index: 4466969 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.2311. Min Act: -0.1700
Data Index: 229770 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.2311. Min Act: -0.1700
Data Index: 3662197 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.2311. Min Act: -0.1700
Data Index: 6358744 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1999. Min Act: -0.1700
Data Index: 5866171 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1686. Min Act: -0.1700
Data Index: 503877 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1686. Min Act: -0.1700
Data Index: 8401727 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1686. Min Act: -0.1700
Data Index: 4266619 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1686. Min Act: -0.1700
Data Index: 2132313 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1374. Min Act: -0.1700
Data Index: 3254180 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1061. Min Act: -0.1700
Data Index: 6529919 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1061. Min Act: -0.1700
Data Index: 5874870 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6999. Min Range: -5.6999
Max Act: 5.1061. Min Act: -0.1700
Data Index: 2062147 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19