Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4206 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.4391. Min Act: -0.1700
Data Index: 7368965 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.2516. Min Act: -0.1700
Data Index: 331776 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.3141. Min Act: -0.1700
Data Index: 4312874 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.3141. Min Act: -0.1700
Data Index: 535076 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.1891. Min Act: -0.1700
Data Index: 7016518 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.1266. Min Act: -0.1700
Data Index: 8060581 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.1266. Min Act: -0.1700
Data Index: 5002352 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.1266. Min Act: -0.1700
Data Index: 1912459 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.0641. Min Act: -0.1700
Data Index: 2178257 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 8300086 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.0641. Min Act: -0.1700
Data Index: 6772414 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 8257583 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.9391. Min Act: -0.1700
Data Index: 5525310 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.9391. Min Act: -0.1700
Data Index: 5459587 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.9391. Min Act: -0.1700
Data Index: 207603 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.9391. Min Act: -0.1700
Data Index: 1650474 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4391. Min Range: -8.4391
Max Act: 8.0016. Min Act: -0.1700
Data Index: 4310707 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.9391. Min Act: -0.1700
Data Index: 2368912 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.8766. Min Act: -0.1700
Data Index: 2294907 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4391. Min Range: -8.4391
Max Act: 7.8766. Min Act: -0.1700
Data Index: 6512423 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19