Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.2787. Min Act: -0.1700
Data Index: 6305351 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.2162. Min Act: -0.1700
Data Index: 6874918 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1849. Min Act: -0.1700
Data Index: 6210603 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1849. Min Act: -0.1700
Data Index: 5247329 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1849. Min Act: -0.1700
Data Index: 3657120 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1849. Min Act: -0.1700
Data Index: 8432967 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1849. Min Act: -0.1700
Data Index: 376107 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1849. Min Act: -0.1700
Data Index: 7661807 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1537. Min Act: -0.1700
Data Index: 1031400 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1224. Min Act: -0.1700
Data Index: 2410888 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1224. Min Act: -0.1700
Data Index: 4757789 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1224. Min Act: -0.1700
Data Index: 6407541 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0911. Min Act: -0.1700
Data Index: 6002483 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0911. Min Act: -0.1700
Data Index: 6881533 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0286. Min Act: -0.1700
Data Index: 2744447 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 4971308 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 5945931 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 241273 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 8812337 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0286. Min Act: -0.1700
Data Index: 5412832 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19