Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.8212. Min Act: -0.1700
Data Index: 2944175 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.5399. Min Act: -0.1700
Data Index: 9269 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.4774. Min Act: -0.1700
Data Index: 8254190 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.4462. Min Act: -0.1700
Data Index: 8453866 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.4462. Min Act: -0.1700
Data Index: 7592830 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.4462. Min Act: -0.1700
Data Index: 4083440 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.2587. Min Act: -0.1700
Data Index: 3188091 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.2899. Min Act: -0.1700
Data Index: 1628174 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.2587. Min Act: -0.1700
Data Index: 8004342 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1962. Min Act: -0.1700
Data Index: 2670010 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1649. Min Act: -0.1700
Data Index: 6625569 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1649. Min Act: -0.1700
Data Index: 7087564 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1649. Min Act: -0.1700
Data Index: 5593619 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1337. Min Act: -0.1700
Data Index: 1933711 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1337. Min Act: -0.1700
Data Index: 863944 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1337. Min Act: -0.1700
Data Index: 6696963 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.0712. Min Act: -0.1700
Data Index: 6781401 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.1024. Min Act: -0.1700
Data Index: 3126425 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.0712. Min Act: -0.1700
Data Index: 1272343 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8212. Min Range: -7.8212
Max Act: 7.0399. Min Act: -0.1700
Data Index: 675747 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19