Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.3306. Min Act: -0.1700
Data Index: 7251824 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2369. Min Act: -0.1700
Data Index: 5485840 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2369. Min Act: -0.1700
Data Index: 4619162 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2369. Min Act: -0.1700
Data Index: 224810 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2369. Min Act: -0.1700
Data Index: 3213421 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2056. Min Act: -0.1700
Data Index: 2459978 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2056. Min Act: -0.1700
Data Index: 3756271 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.2056. Min Act: -0.1700
Data Index: 3062378 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 8363893 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 6688747 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 6584391 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 6927382 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 5140636 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 5198307 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1744. Min Act: -0.1700
Data Index: 8353999 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1119. Min Act: -0.1700
Data Index: 5516768 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1431. Min Act: -0.1700
Data Index: 1195877 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1431. Min Act: -0.1700
Data Index: 2558046 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1119. Min Act: -0.1700
Data Index: 4111091 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3306. Min Range: -5.3306
Max Act: 5.1119. Min Act: -0.1700
Data Index: 1032877 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19