Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1632 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0822. Min Range: -3.0822
Max Act: 3.0822. Min Act: -0.1700
Data Index: 22022 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0822. Min Range: -3.0822
Max Act: 3.0507. Min Act: -0.1700
Data Index: 6457019 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.9083. Min Act: -0.1700
Data Index: 882967 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.9083. Min Act: -0.1700
Data Index: 7240383 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.9083. Min Act: -0.1700
Data Index: 1519307 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.9083. Min Act: -0.1700
Data Index: 3977048 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8925. Min Act: -0.1700
Data Index: 2985574 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8766. Min Act: -0.1700
Data Index: 2968966 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8925. Min Act: -0.1700
Data Index: 8464530 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8449. Min Act: -0.1700
Data Index: 4372825 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8449. Min Act: -0.1700
Data Index: 8627809 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8290. Min Act: -0.1700
Data Index: 5535992 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8290. Min Act: -0.1700
Data Index: 3042207 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.8290. Min Act: -0.1700
Data Index: 2665757 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.7971. Min Act: -0.1700
Data Index: 3230237 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.7971. Min Act: -0.1700
Data Index: 7056058 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.7812. Min Act: -0.1700
Data Index: 8177878 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.7652. Min Act: -0.1700
Data Index: 1016930 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.7812. Min Act: -0.1700
Data Index: 1872852 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0822. Min Range: -3.0822
Max Act: 2.7812. Min Act: -0.1700
Data Index: 6580100 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19