Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 1104517 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6244. Min Act: -0.1700
Data Index: 4069896 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5932. Min Act: -0.1700
Data Index: 4635713 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5619. Min Act: -0.1700
Data Index: 2130277 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5307. Min Act: -0.1700
Data Index: 7886865 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 957248 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4994. Min Act: -0.1700
Data Index: 4784884 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4369. Min Act: -0.1700
Data Index: 843554 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4369. Min Act: -0.1700
Data Index: 4432223 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4369. Min Act: -0.1700
Data Index: 6985951 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4057. Min Act: -0.1700
Data Index: 3247337 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4057. Min Act: -0.1700
Data Index: 2300509 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.4057. Min Act: -0.1700
Data Index: 5801089 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3744. Min Act: -0.1700
Data Index: 6985428 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3744. Min Act: -0.1700
Data Index: 4120915 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3432. Min Act: -0.1700
Data Index: 4965517 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3432. Min Act: -0.1700
Data Index: 2141873 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3119. Min Act: -0.1700
Data Index: 1688234 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7645170 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3744. Min Act: -0.1700
Data Index: 5870632 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19