Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2252 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1925. Min Range: -7.1925
Max Act: 7.1925. Min Act: -0.1700
Data Index: 2050988 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1925. Min Range: -7.1925
Max Act: 7.1613. Min Act: -0.1700
Data Index: 5905556 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1925. Min Range: -7.1925
Max Act: 7.0988. Min Act: -0.1700
Data Index: 42520 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1925. Min Range: -7.1925
Max Act: 7.0050. Min Act: -0.1700
Data Index: 5715042 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.9738. Min Act: -0.1700
Data Index: 3771103 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.9425. Min Act: -0.1700
Data Index: 3560513 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.8800. Min Act: -0.1700
Data Index: 6146192 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.8800. Min Act: -0.1700
Data Index: 6226679 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.8800. Min Act: -0.1700
Data Index: 6310212 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.8488. Min Act: -0.1700
Data Index: 8407231 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.8175. Min Act: -0.1700
Data Index: 4482921 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7863. Min Act: -0.1700
Data Index: 3471435 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7863. Min Act: -0.1700
Data Index: 1233443 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.8175. Min Act: -0.1700
Data Index: 8301533 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6093115 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7550. Min Act: -0.1700
Data Index: 379121 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7550. Min Act: -0.1700
Data Index: 2883340 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7550. Min Act: -0.1700
Data Index: 2947096 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7550. Min Act: -0.1700
Data Index: 4306200 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1925. Min Range: -7.1925
Max Act: 6.7238. Min Act: -0.1700
Data Index: 3537000 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19