Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1968. Min Range: -6.1968
Max Act: 6.1656. Min Act: -0.1700
Data Index: 1418304 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1968. Min Range: -6.1968
Max Act: 6.1968. Min Act: -0.1700
Data Index: 5243304 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1968. Min Range: -6.1968
Max Act: 6.0406. Min Act: -0.1700
Data Index: 1313022 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.9781. Min Act: -0.1700
Data Index: 3399137 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.9468. Min Act: -0.1700
Data Index: 6148403 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.9468. Min Act: -0.1700
Data Index: 4222184 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.9156. Min Act: -0.1700
Data Index: 4996909 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.9156. Min Act: -0.1700
Data Index: 5290904 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8843. Min Act: -0.1700
Data Index: 2118005 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8843. Min Act: -0.1700
Data Index: 699887 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8843. Min Act: -0.1700
Data Index: 5752940 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.9156. Min Act: -0.1700
Data Index: 4444839 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8531. Min Act: -0.1700
Data Index: 6071828 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8531. Min Act: -0.1700
Data Index: 3399143 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8531. Min Act: -0.1700
Data Index: 6722115 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8531. Min Act: -0.1700
Data Index: 324273 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8531. Min Act: -0.1700
Data Index: 4411409 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8531. Min Act: -0.1700
Data Index: 5850235 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8218. Min Act: -0.1700
Data Index: 4222185 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1968. Min Range: -6.1968
Max Act: 5.8218. Min Act: -0.1700
Data Index: 467326 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19