Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4237 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 4802143 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 2635303 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 7798845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 2568587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 2568246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 4433238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 4338342 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 6517604 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 6324432 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 5536622 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.6096. Min Act: -0.1700
Data Index: 7476079 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 166462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5939. Min Act: -0.1700
Data Index: 7163703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5486999 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.4686. Min Act: -0.1700
Data Index: 1719660 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.4373. Min Act: -0.1700
Data Index: 3826823 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.3903. Min Act: -0.1700
Data Index: 7842642 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.3903. Min Act: -0.1700
Data Index: 6674464 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.3903. Min Act: -0.1700
Data Index: 366882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6096. Min Range: -3.6096
Max Act: 3.3746. Min Act: -0.1700
Data Index: 4314103 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19