Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2042 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.2062. Min Act: -0.1700
Data Index: 1653802 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.1750. Min Act: -0.1700
Data Index: 1110728 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.1437. Min Act: -0.1700
Data Index: 3316514 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.1125. Min Act: -0.1700
Data Index: 609617 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.0812. Min Act: -0.1700
Data Index: 4408005 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.0187. Min Act: -0.1700
Data Index: 8744165 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.0187. Min Act: -0.1700
Data Index: 1278688 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2062. Min Range: -5.2062
Max Act: 5.0187. Min Act: -0.1700
Data Index: 4228854 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9875. Min Act: -0.1700
Data Index: 7536991 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9562. Min Act: -0.1700
Data Index: 6903049 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9562. Min Act: -0.1700
Data Index: 1544955 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9562. Min Act: -0.1700
Data Index: 518559 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9250. Min Act: -0.1700
Data Index: 8299842 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9562. Min Act: -0.1700
Data Index: 8445047 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.9250. Min Act: -0.1700
Data Index: 6272302 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.8937. Min Act: -0.1700
Data Index: 2147229 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.8937. Min Act: -0.1700
Data Index: 1648949 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.8937. Min Act: -0.1700
Data Index: 7084184 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.8937. Min Act: -0.1700
Data Index: 3723429 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2062. Min Range: -5.2062
Max Act: 4.8937. Min Act: -0.1700
Data Index: 2845485 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19