Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.8074. Min Act: -0.1700
Data Index: 7660759 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.7449. Min Act: -0.1700
Data Index: 3542091 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.5574. Min Act: -0.1700
Data Index: 6941215 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.4637. Min Act: -0.1700
Data Index: 1148155 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.4324. Min Act: -0.1700
Data Index: 8132440 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.3699. Min Act: -0.1700
Data Index: 5303580 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.3387. Min Act: -0.1700
Data Index: 2689419 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.3074. Min Act: -0.1700
Data Index: 823891 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.1824. Min Act: -0.1700
Data Index: 1087175 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.1512. Min Act: -0.1700
Data Index: 2478771 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.1199. Min Act: -0.1700
Data Index: 7159163 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0574. Min Act: -0.1700
Data Index: 2320354 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0574. Min Act: -0.1700
Data Index: 6315372 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0262. Min Act: -0.1700
Data Index: 3468877 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0262. Min Act: -0.1700
Data Index: 7840675 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1955532 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0574. Min Act: -0.1700
Data Index: 3520968 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0262. Min Act: -0.1700
Data Index: 7750810 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8074. Min Range: -7.8074
Max Act: 7.0262. Min Act: -0.1700
Data Index: 2530122 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8074. Min Range: -7.8074
Max Act: 6.9949. Min Act: -0.1700
Data Index: 2159705 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19