Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2289 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.7615. Min Act: -0.1700
Data Index: 7000689 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.7302. Min Act: -0.1700
Data Index: 1538338 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.6365. Min Act: -0.1700
Data Index: 3025698 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6249151 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.5740. Min Act: -0.1700
Data Index: 658841 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.5740. Min Act: -0.1700
Data Index: 5554595 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.5427. Min Act: -0.1700
Data Index: 7073718 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4802. Min Act: -0.1700
Data Index: 8645693 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4802. Min Act: -0.1700
Data Index: 4298805 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4177. Min Act: -0.1700
Data Index: 3782872 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4490. Min Act: -0.1700
Data Index: 459576 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4177. Min Act: -0.1700
Data Index: 2949415 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4177. Min Act: -0.1700
Data Index: 7913565 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4177. Min Act: -0.1700
Data Index: 8051865 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4490. Min Act: -0.1700
Data Index: 2896961 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.4490. Min Act: -0.1700
Data Index: 5408626 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.3865. Min Act: -0.1700
Data Index: 1107006 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.3865. Min Act: -0.1700
Data Index: 8642033 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.3552. Min Act: -0.1700
Data Index: 6451198 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7615. Min Range: -5.7615
Max Act: 5.3552. Min Act: -0.1700
Data Index: 7122812 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19