Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.8113. Min Act: -0.1700
Data Index: 3547277 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.7945. Min Act: -0.1700
Data Index: 4635463 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.7612. Min Act: -0.1700
Data Index: 2976895 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.7695. Min Act: -0.1700
Data Index: 2117595 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.7529. Min Act: -0.1700
Data Index: 4040986 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.7117. Min Act: -0.1700
Data Index: 5490114 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6872. Min Act: -0.1700
Data Index: 5056239 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6389. Min Act: -0.1700
Data Index: 2113425 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6309. Min Act: -0.1700
Data Index: 7937624 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6229. Min Act: -0.1700
Data Index: 7832099 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6309. Min Act: -0.1700
Data Index: 2976897 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6229. Min Act: -0.1698
Data Index: 2857617 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6229. Min Act: -0.1700
Data Index: 100325 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6150. Min Act: -0.1700
Data Index: 2801753 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6150. Min Act: -0.1699
Data Index: 273635 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.6071. Min Act: -0.1693
Data Index: 5869221 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.5992. Min Act: -0.1700
Data Index: 7060940 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.5992. Min Act: -0.1700
Data Index: 6491668 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.5835. Min Act: -0.1700
Data Index: 3027749 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8113. Min Range: -0.8113
Max Act: 0.5835. Min Act: -0.1700
Data Index: 4339171 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19