Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0111. Min Range: -5.0111
Max Act: 5.0111. Min Act: -0.1700
Data Index: 3540306 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.9798. Min Act: -0.1700
Data Index: 513521 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.9173. Min Act: -0.1700
Data Index: 3067420 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8861. Min Act: -0.1700
Data Index: 4175002 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8861. Min Act: -0.1700
Data Index: 6990602 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8861. Min Act: -0.1700
Data Index: 5007485 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8548. Min Act: -0.1700
Data Index: 5581963 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8548. Min Act: -0.1700
Data Index: 2784799 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8548. Min Act: -0.1700
Data Index: 2560920 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 6185523 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 5789855 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 3936442 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 311236 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 1547238 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 7142612 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 2320484 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.7923. Min Act: -0.1700
Data Index: 307019 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.7923. Min Act: -0.1700
Data Index: 20583 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.7923. Min Act: -0.1700
Data Index: 4062999 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8236. Min Act: -0.1700
Data Index: 398516 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19