Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.4818. Min Act: -0.1700
Data Index: 4979883 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.4818. Min Act: -0.1700
Data Index: 7394462 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.4193. Min Act: -0.1700
Data Index: 1827797 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.3256. Min Act: -0.1700
Data Index: 6618341 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.3256. Min Act: -0.1700
Data Index: 7478816 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2943. Min Act: -0.1700
Data Index: 7258268 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2943. Min Act: -0.1700
Data Index: 7250560 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2631. Min Act: -0.1700
Data Index: 2670009 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2006. Min Act: -0.1700
Data Index: 2464512 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2318. Min Act: -0.1700
Data Index: 5471781 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2006. Min Act: -0.1700
Data Index: 4979189 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 491718 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 3466800 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 511564 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 2059593 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 5801296 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 8452677 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 88851 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 7177176 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 6669499 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19