Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1235. Min Range: -8.1235
Max Act: 8.1235. Min Act: -0.1700
Data Index: 379093 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1235. Min Range: -8.1235
Max Act: 8.1235. Min Act: -0.1700
Data Index: 8374160 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.9985. Min Act: -0.1700
Data Index: 6135309 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.6235. Min Act: -0.1700
Data Index: 3291690 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.5923. Min Act: -0.1700
Data Index: 3335561 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.5923. Min Act: -0.1700
Data Index: 5120599 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.4985. Min Act: -0.1700
Data Index: 91017 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.4673. Min Act: -0.1700
Data Index: 1594765 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.4673. Min Act: -0.1700
Data Index: 3037454 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.4360. Min Act: -0.1700
Data Index: 5221507 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.4048. Min Act: -0.1700
Data Index: 1643478 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.3735. Min Act: -0.1700
Data Index: 7736639 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.3423. Min Act: -0.1700
Data Index: 5551463 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.3110. Min Act: -0.1700
Data Index: 1027450 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.2798. Min Act: -0.1700
Data Index: 4476599 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.3110. Min Act: -0.1700
Data Index: 768237 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.3110. Min Act: -0.1700
Data Index: 6731773 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.2485. Min Act: -0.1700
Data Index: 8481938 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.2485. Min Act: -0.1700
Data Index: 6637691 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1235. Min Range: -8.1235
Max Act: 7.2173. Min Act: -0.1700
Data Index: 8101281 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19