Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1530. Min Range: -8.1530
Max Act: 8.1530. Min Act: -0.1700
Data Index: 3185740 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.9655. Min Act: -0.1700
Data Index: 8191645 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.9030. Min Act: -0.1700
Data Index: 729689 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.9030. Min Act: -0.1700
Data Index: 7804990 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.8405. Min Act: -0.1700
Data Index: 1455764 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.6842. Min Act: -0.1700
Data Index: 2859963 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.6530. Min Act: -0.1700
Data Index: 3376779 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.6217. Min Act: -0.1700
Data Index: 5895296 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.6217. Min Act: -0.1700
Data Index: 2096333 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.4967. Min Act: -0.1700
Data Index: 179229 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.4967. Min Act: -0.1700
Data Index: 4585364 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.4342. Min Act: -0.1700
Data Index: 1541812 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.4655. Min Act: -0.1700
Data Index: 627559 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3717. Min Act: -0.1700
Data Index: 5651213 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3717. Min Act: -0.1700
Data Index: 3697620 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3717. Min Act: -0.1700
Data Index: 2131396 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3717. Min Act: -0.1700
Data Index: 123427 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3717. Min Act: -0.1700
Data Index: 5338328 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3092. Min Act: -0.1700
Data Index: 369564 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1530. Min Range: -8.1530
Max Act: 7.3405. Min Act: -0.1700
Data Index: 2260387 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19