Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5529 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0839. Min Range: -4.0839
Max Act: 4.0839. Min Act: -0.1700
Data Index: 5089817 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.9589. Min Act: -0.1700
Data Index: 7921086 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.9276. Min Act: -0.1700
Data Index: 1555720 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.8338. Min Act: -0.1700
Data Index: 3946020 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.8025. Min Act: -0.1700
Data Index: 578694 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7087. Min Act: -0.1700
Data Index: 8539801 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7087. Min Act: -0.1700
Data Index: 3801485 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7243. Min Act: -0.1700
Data Index: 8102700 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7400. Min Act: -0.1700
Data Index: 1555721 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7243. Min Act: -0.1700
Data Index: 3566367 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7087. Min Act: -0.1700
Data Index: 5547008 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.7243. Min Act: -0.1700
Data Index: 8764632 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6774. Min Act: -0.1700
Data Index: 4981688 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6618. Min Act: -0.1700
Data Index: 8358314 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6618. Min Act: -0.1700
Data Index: 509695 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6461. Min Act: -0.1700
Data Index: 8210118 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6618. Min Act: -0.1700
Data Index: 2322097 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6461. Min Act: -0.1700
Data Index: 488099 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6305. Min Act: -0.1700
Data Index: 1699524 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0839. Min Range: -4.0839
Max Act: 3.6305. Min Act: -0.1700
Data Index: 7611881 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19