Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.3322. Min Act: -0.1700
Data Index: 6866705 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.3010. Min Act: -0.1700
Data Index: 4210401 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.2697. Min Act: -0.1700
Data Index: 8459137 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.3010. Min Act: -0.1700
Data Index: 7044697 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.2697. Min Act: -0.1700
Data Index: 5881114 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.2385. Min Act: -0.1700
Data Index: 5435641 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.1447. Min Act: -0.1700
Data Index: 4210400 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.1447. Min Act: -0.1700
Data Index: 8660016 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.1447. Min Act: -0.1700
Data Index: 483542 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.1447. Min Act: -0.1700
Data Index: 1640466 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.1135. Min Act: -0.1700
Data Index: 8581207 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.0822. Min Act: -0.1700
Data Index: 6010722 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.0197. Min Act: -0.1700
Data Index: 6576672 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.0197. Min Act: -0.1700
Data Index: 3535521 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3322. Min Range: -5.3322
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4443254 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3322. Min Range: -5.3322
Max Act: 4.9885. Min Act: -0.1700
Data Index: 3908634 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3322. Min Range: -5.3322
Max Act: 4.9885. Min Act: -0.1700
Data Index: 4171811 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3322. Min Range: -5.3322
Max Act: 4.9885. Min Act: -0.1700
Data Index: 7518890 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3322. Min Range: -5.3322
Max Act: 4.9885. Min Act: -0.1700
Data Index: 3293142 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3322. Min Range: -5.3322
Max Act: 4.9885. Min Act: -0.1700
Data Index: 8445011 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19