Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.8792. Min Act: -0.1700
Data Index: 4414604 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.7854. Min Act: -0.1700
Data Index: 436575 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.7229. Min Act: -0.1700
Data Index: 7690794 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.7229. Min Act: -0.1700
Data Index: 7256864 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1895595 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.6604. Min Act: -0.1700
Data Index: 1512968 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.6604. Min Act: -0.1700
Data Index: 849373 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.6292. Min Act: -0.1700
Data Index: 3157319 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.6292. Min Act: -0.1700
Data Index: 5866771 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5979. Min Act: -0.1700
Data Index: 3340090 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5667. Min Act: -0.1700
Data Index: 587210 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5979. Min Act: -0.1700
Data Index: 3077775 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5667. Min Act: -0.1700
Data Index: 5739340 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5354. Min Act: -0.1700
Data Index: 3348330 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5354. Min Act: -0.1700
Data Index: 1552863 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5042. Min Act: -0.1700
Data Index: 1207552 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5042. Min Act: -0.1700
Data Index: 1675910 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5042. Min Act: -0.1700
Data Index: 2650271 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5042. Min Act: -0.1700
Data Index: 2071582 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8792. Min Range: -5.8792
Max Act: 5.5042. Min Act: -0.1700
Data Index: 5492256 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19