Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4211. Min Range: -7.4211
Max Act: 7.4211. Min Act: -0.1700
Data Index: 8094154 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4211. Min Range: -7.4211
Max Act: 7.2336. Min Act: -0.1700
Data Index: 8477022 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4211. Min Range: -7.4211
Max Act: 7.2024. Min Act: -0.1700
Data Index: 5232722 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4211. Min Range: -7.4211
Max Act: 7.0774. Min Act: -0.1700
Data Index: 2401029 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4211. Min Range: -7.4211
Max Act: 7.1086. Min Act: -0.1700
Data Index: 8448866 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4211. Min Range: -7.4211
Max Act: 7.0149. Min Act: -0.1700
Data Index: 1712860 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.9524. Min Act: -0.1700
Data Index: 7859279 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.8899. Min Act: -0.1700
Data Index: 5853217 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.8586. Min Act: -0.1700
Data Index: 3675778 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.8274. Min Act: -0.1700
Data Index: 6834635 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.8274. Min Act: -0.1700
Data Index: 3863253 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7961. Min Act: -0.1700
Data Index: 2068084 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7961. Min Act: -0.1700
Data Index: 5751169 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7336. Min Act: -0.1700
Data Index: 2786037 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7336. Min Act: -0.1700
Data Index: 5843788 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7024. Min Act: -0.1700
Data Index: 8085535 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7024. Min Act: -0.1700
Data Index: 4169184 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.7024. Min Act: -0.1700
Data Index: 3143535 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.6711. Min Act: -0.1700
Data Index: 2434128 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4211. Min Range: -7.4211
Max Act: 6.6711. Min Act: -0.1700
Data Index: 124459 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19