Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.8092. Min Act: -0.1700
Data Index: 1742462 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.6841. Min Act: -0.1700
Data Index: 8120857 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.6684. Min Act: -0.1700
Data Index: 4712502 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.6528. Min Act: -0.1700
Data Index: 3772111 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.6215. Min Act: -0.1700
Data Index: 1270191 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.6215. Min Act: -0.1700
Data Index: 5934966 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.6058. Min Act: -0.1700
Data Index: 1821803 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5902. Min Act: -0.1700
Data Index: 7325331 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5745. Min Act: -0.1700
Data Index: 8636263 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5745. Min Act: -0.1700
Data Index: 1738495 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5745. Min Act: -0.1700
Data Index: 265154 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5745. Min Act: -0.1700
Data Index: 6221163 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5589. Min Act: -0.1700
Data Index: 3864708 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5589. Min Act: -0.1700
Data Index: 333538 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5432. Min Act: -0.1700
Data Index: 719043 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.5119. Min Act: -0.1700
Data Index: 4883313 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.4962. Min Act: -0.1700
Data Index: 3681091 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.4649. Min Act: -0.1700
Data Index: 5954410 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.4806. Min Act: -0.1700
Data Index: 6637083 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8092. Min Range: -3.8092
Max Act: 3.4806. Min Act: -0.1700
Data Index: 7908012 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19