Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6231 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4165. Min Range: -8.4165
Max Act: 8.4165. Min Act: -0.1700
Data Index: 4574876 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4165. Min Range: -8.4165
Max Act: 8.2915. Min Act: -0.1700
Data Index: 556971 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.8540. Min Act: -0.1700
Data Index: 2394746 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.7290. Min Act: -0.1700
Data Index: 492801 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.6665. Min Act: -0.1700
Data Index: 1761859 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.6665. Min Act: -0.1700
Data Index: 3719468 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.6040. Min Act: -0.1700
Data Index: 8642299 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.6040. Min Act: -0.1700
Data Index: 1495350 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.6040. Min Act: -0.1700
Data Index: 2477348 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5728. Min Act: -0.1700
Data Index: 8578112 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.6040. Min Act: -0.1700
Data Index: 8695908 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5415. Min Act: -0.1700
Data Index: 3323333 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5728. Min Act: -0.1700
Data Index: 4695327 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5728. Min Act: -0.1700
Data Index: 1155532 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5728. Min Act: -0.1700
Data Index: 4626813 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5415. Min Act: -0.1700
Data Index: 8712043 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5415. Min Act: -0.1700
Data Index: 6593058 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5415. Min Act: -0.1700
Data Index: 7835449 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.5103. Min Act: -0.1700
Data Index: 1785900 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4165. Min Range: -8.4165
Max Act: 7.4478. Min Act: -0.1700
Data Index: 1628836 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19