Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.9632. Min Act: -0.1700
Data Index: 4353029 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.9320. Min Act: -0.1700
Data Index: 7886151 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.7757. Min Act: -0.1700
Data Index: 5764705 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.7445. Min Act: -0.1700
Data Index: 949062 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.7132. Min Act: -0.1700
Data Index: 1342106 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.6820. Min Act: -0.1700
Data Index: 407889 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.6820. Min Act: -0.1700
Data Index: 5565303 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.6507. Min Act: -0.1700
Data Index: 669380 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.7132. Min Act: -0.1700
Data Index: 5309447 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.6820. Min Act: -0.1700
Data Index: 3321100 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.6507. Min Act: -0.1700
Data Index: 6918216 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.6507. Min Act: -0.1700
Data Index: 7500760 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5882. Min Act: -0.1700
Data Index: 2709030 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5882. Min Act: -0.1700
Data Index: 6110920 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5882. Min Act: -0.1700
Data Index: 8419765 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5570. Min Act: -0.1700
Data Index: 427777 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5570. Min Act: -0.1700
Data Index: 3513946 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5570. Min Act: -0.1700
Data Index: 7161397 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5570. Min Act: -0.1700
Data Index: 494881 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9632. Min Range: -6.9632
Max Act: 6.5882. Min Act: -0.1700
Data Index: 6865394 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19