Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.5256. Min Act: -0.1700
Data Index: 5966458 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.4629. Min Act: -0.1700
Data Index: 1359719 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.4629. Min Act: -0.1700
Data Index: 5808142 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.4159. Min Act: -0.1700
Data Index: 4163167 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.3689. Min Act: -0.1700
Data Index: 3000358 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.3061. Min Act: -0.1700
Data Index: 4163168 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2904. Min Act: -0.1700
Data Index: 8541085 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2747. Min Act: -0.1700
Data Index: 6525091 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2747. Min Act: -0.1700
Data Index: 937410 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2590. Min Act: -0.1700
Data Index: 97077 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2590. Min Act: -0.1700
Data Index: 8598820 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2433. Min Act: -0.1700
Data Index: 4943780 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2590. Min Act: -0.1700
Data Index: 4695447 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2433. Min Act: -0.1700
Data Index: 4294379 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2433. Min Act: -0.1700
Data Index: 5092149 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2433. Min Act: -0.1700
Data Index: 937408 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2276. Min Act: -0.1700
Data Index: 2803878 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2276. Min Act: -0.1700
Data Index: 6611131 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2276. Min Act: -0.1700
Data Index: 6358615 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5256. Min Range: -3.5256
Max Act: 3.2276. Min Act: -0.1700
Data Index: 8062209 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19