Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2589. Min Range: -6.2589
Max Act: 6.2589. Min Act: -0.1700
Data Index: 8279380 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2589. Min Range: -6.2589
Max Act: 6.2276. Min Act: -0.1700
Data Index: 5830277 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.8526. Min Act: -0.1700
Data Index: 7288406 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.7901. Min Act: -0.1700
Data Index: 8410795 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.7901. Min Act: -0.1700
Data Index: 6217142 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.7901. Min Act: -0.1700
Data Index: 3743708 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.7589. Min Act: -0.1700
Data Index: 5061719 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.7276. Min Act: -0.1700
Data Index: 3541294 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6964. Min Act: -0.1700
Data Index: 4789094 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6964. Min Act: -0.1700
Data Index: 7238006 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6651. Min Act: -0.1700
Data Index: 4362141 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6964. Min Act: -0.1700
Data Index: 6280302 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6964. Min Act: -0.1700
Data Index: 7704720 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6651. Min Act: -0.1700
Data Index: 4024199 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.6339. Min Act: -0.1700
Data Index: 4045243 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.5714. Min Act: -0.1700
Data Index: 8273812 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.5714. Min Act: -0.1700
Data Index: 7262882 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.5714. Min Act: -0.1700
Data Index: 7062482 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.5714. Min Act: -0.1700
Data Index: 796874 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2589. Min Range: -6.2589
Max Act: 5.5714. Min Act: -0.1700
Data Index: 5270422 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19