Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.5322. Min Act: -0.1700
Data Index: 7613135 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.1884. Min Act: -0.1700
Data Index: 679029 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.1572. Min Act: -0.1700
Data Index: 3221067 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.1572. Min Act: -0.1700
Data Index: 5736310 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.1259. Min Act: -0.1700
Data Index: 59345 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.1259. Min Act: -0.1700
Data Index: 3897118 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.0634. Min Act: -0.1700
Data Index: 6925379 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.0009. Min Act: -0.1700
Data Index: 864968 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.0322. Min Act: -0.1700
Data Index: 5174829 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.0322. Min Act: -0.1700
Data Index: 2229318 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5322. Min Range: -7.5322
Max Act: 7.0009. Min Act: -0.1700
Data Index: 4019553 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.9072. Min Act: -0.1700
Data Index: 441478 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.9072. Min Act: -0.1700
Data Index: 4869516 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.8447. Min Act: -0.1700
Data Index: 5155137 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.9072. Min Act: -0.1700
Data Index: 6445359 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.8759. Min Act: -0.1700
Data Index: 6714817 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.8447. Min Act: -0.1700
Data Index: 5026162 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.8447. Min Act: -0.1700
Data Index: 852179 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.8447. Min Act: -0.1700
Data Index: 3430458 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5322. Min Range: -7.5322
Max Act: 6.8134. Min Act: -0.1700
Data Index: 3643388 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19