Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 709 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.8589. Min Act: -0.1700
Data Index: 5816212 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.8589. Min Act: -0.1700
Data Index: 1496637 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.8276. Min Act: -0.1700
Data Index: 5821735 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7964. Min Act: -0.1700
Data Index: 2487048 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.8276. Min Act: -0.1700
Data Index: 1948851 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7964. Min Act: -0.1700
Data Index: 105658 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7339. Min Act: -0.1700
Data Index: 869880 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7651. Min Act: -0.1700
Data Index: 8537334 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7651. Min Act: -0.1700
Data Index: 7799576 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7651. Min Act: -0.1700
Data Index: 3085470 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7026. Min Act: -0.1700
Data Index: 2816927 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.7026. Min Act: -0.1700
Data Index: 6326122 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6714. Min Act: -0.1700
Data Index: 2158763 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6714. Min Act: -0.1700
Data Index: 4533877 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6714. Min Act: -0.1700
Data Index: 788838 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6714. Min Act: -0.1700
Data Index: 8358094 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6401. Min Act: -0.1700
Data Index: 1589148 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6401. Min Act: -0.1700
Data Index: 437654 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6401. Min Act: -0.1700
Data Index: 803660 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8589. Min Range: -4.8589
Max Act: 4.6089. Min Act: -0.1700
Data Index: 3443542 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19