Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0571. Min Range: -6.0571
Max Act: 6.0571. Min Act: -0.1700
Data Index: 6548345 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0571. Min Range: -6.0571
Max Act: 6.0571. Min Act: -0.1700
Data Index: 7044252 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.9946. Min Act: -0.1700
Data Index: 7881143 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.9634. Min Act: -0.1700
Data Index: 7029430 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.9321. Min Act: -0.1700
Data Index: 3470141 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.8696. Min Act: -0.1700
Data Index: 6898189 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.8696. Min Act: -0.1700
Data Index: 8134179 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7446. Min Act: -0.1700
Data Index: 2007792 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7759. Min Act: -0.1700
Data Index: 8177594 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7446. Min Act: -0.1700
Data Index: 2637489 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7759. Min Act: -0.1700
Data Index: 2015382 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7446. Min Act: -0.1700
Data Index: 6992263 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7446. Min Act: -0.1700
Data Index: 8213154 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7134. Min Act: -0.1700
Data Index: 2262921 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7134. Min Act: -0.1700
Data Index: 1176043 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7134. Min Act: -0.1700
Data Index: 6336665 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7134. Min Act: -0.1700
Data Index: 1175153 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7134. Min Act: -0.1700
Data Index: 7166434 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.7134. Min Act: -0.1700
Data Index: 6055962 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0571. Min Range: -6.0571
Max Act: 5.6821. Min Act: -0.1700
Data Index: 3893097 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19