Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.5841. Min Act: -0.1700
Data Index: 7668574 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.4904. Min Act: -0.1700
Data Index: 3009949 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.4591. Min Act: -0.1700
Data Index: 3692573 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.4591. Min Act: -0.1700
Data Index: 88748 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.4279. Min Act: -0.1700
Data Index: 4932805 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.4279. Min Act: -0.1700
Data Index: 7093844 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.3341. Min Act: -0.1700
Data Index: 4082098 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.3029. Min Act: -0.1700
Data Index: 1377331 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.2404. Min Act: -0.1700
Data Index: 1377326 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.2404. Min Act: -0.1700
Data Index: 4117770 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.2404. Min Act: -0.1700
Data Index: 1089417 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1779. Min Act: -0.1700
Data Index: 5094083 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.2091. Min Act: -0.1700
Data Index: 7918772 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1779. Min Act: -0.1700
Data Index: 3877156 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1779. Min Act: -0.1700
Data Index: 1175992 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1466. Min Act: -0.1700
Data Index: 2841428 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1466. Min Act: -0.1700
Data Index: 8617817 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1466. Min Act: -0.1700
Data Index: 5750043 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1466. Min Act: -0.1700
Data Index: 1738871 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5841. Min Range: -6.5841
Max Act: 6.1466. Min Act: -0.1700
Data Index: 3626072 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19