Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.5633. Min Act: -0.1700
Data Index: 6740189 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.2508. Min Act: -0.1700
Data Index: 99339 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.1883. Min Act: -0.1700
Data Index: 813128 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.1571. Min Act: -0.1700
Data Index: 3545240 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.1258. Min Act: -0.1700
Data Index: 4592782 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.0321. Min Act: -0.1700
Data Index: 2585073 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.0321. Min Act: -0.1700
Data Index: 1281899 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5633. Min Range: -7.5633
Max Act: 7.0008. Min Act: -0.1700
Data Index: 2206183 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9696. Min Act: -0.1700
Data Index: 5505744 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9696. Min Act: -0.1700
Data Index: 400216 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9383. Min Act: -0.1700
Data Index: 3122141 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9383. Min Act: -0.1700
Data Index: 3124437 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9071. Min Act: -0.1700
Data Index: 2674186 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9071. Min Act: -0.1700
Data Index: 2929729 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9071. Min Act: -0.1700
Data Index: 8132012 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.9071. Min Act: -0.1700
Data Index: 4688051 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.8758. Min Act: -0.1700
Data Index: 6791730 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.8446. Min Act: -0.1700
Data Index: 1413009 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.8446. Min Act: -0.1700
Data Index: 689022 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5633. Min Range: -7.5633
Max Act: 6.8446. Min Act: -0.1700
Data Index: 820131 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19