Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5316 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.8644. Min Act: -0.1700
Data Index: 6614202 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.7081. Min Act: -0.1700
Data Index: 5159019 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.6769. Min Act: -0.1700
Data Index: 227825 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.6456. Min Act: -0.1700
Data Index: 8285800 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.6144. Min Act: -0.1700
Data Index: 7324135 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.6456. Min Act: -0.1700
Data Index: 8189463 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.6144. Min Act: -0.1700
Data Index: 8357660 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.5831. Min Act: -0.1700
Data Index: 1706141 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.5831. Min Act: -0.1700
Data Index: 3084695 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.5831. Min Act: -0.1700
Data Index: 5898433 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.5206. Min Act: -0.1700
Data Index: 8320171 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.5206. Min Act: -0.1700
Data Index: 8221445 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.5519. Min Act: -0.1700
Data Index: 6935866 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4894. Min Act: -0.1700
Data Index: 1748366 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4894. Min Act: -0.1700
Data Index: 8507144 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4581. Min Act: -0.1700
Data Index: 7839388 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4581. Min Act: -0.1700
Data Index: 6416714 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4581. Min Act: -0.1700
Data Index: 7747617 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4269. Min Act: -0.1700
Data Index: 6918457 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8644. Min Range: -5.8644
Max Act: 5.4269. Min Act: -0.1700
Data Index: 4360254 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19