Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.5134. Min Act: -0.1700
Data Index: 3012623 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.3259. Min Act: -0.1700
Data Index: 7942166 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.2634. Min Act: -0.1699
Data Index: 3982073 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.2634. Min Act: -0.1700
Data Index: 7802821 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.2009. Min Act: -0.1700
Data Index: 5027552 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.1384. Min Act: -0.1700
Data Index: 6626483 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.0759. Min Act: -0.1700
Data Index: 8299094 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.0759. Min Act: -0.1700
Data Index: 7301877 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 4589181 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 446684 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 3780552 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5134. Min Range: -9.5134
Max Act: 9.0134. Min Act: -0.1700
Data Index: 4781803 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.9509. Min Act: -0.1700
Data Index: 3561063 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.9509. Min Act: -0.1700
Data Index: 1363176 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.9509. Min Act: -0.1700
Data Index: 390551 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.8884. Min Act: -0.1700
Data Index: 1545333 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.8884. Min Act: -0.1700
Data Index: 1100638 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.8884. Min Act: -0.1700
Data Index: 6600960 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.8259. Min Act: -0.1700
Data Index: 2848284 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5134. Min Range: -9.5134
Max Act: 8.8259. Min Act: -0.1700
Data Index: 1222718 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19