Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9060. Min Range: -7.9060
Max Act: 7.9060. Min Act: -0.1700
Data Index: 7294903 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9060. Min Range: -7.9060
Max Act: 7.8435. Min Act: -0.1700
Data Index: 3434332 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9060. Min Range: -7.9060
Max Act: 7.5935. Min Act: -0.1700
Data Index: 2849462 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9060. Min Range: -7.9060
Max Act: 7.4998. Min Act: -0.1700
Data Index: 5098980 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9060. Min Range: -7.9060
Max Act: 7.1248. Min Act: -0.1700
Data Index: 6895652 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9060. Min Range: -7.9060
Max Act: 7.0935. Min Act: -0.1700
Data Index: 5747529 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.9998. Min Act: -0.1700
Data Index: 5387356 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.9998. Min Act: -0.1700
Data Index: 6041899 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.9998. Min Act: -0.1700
Data Index: 4562931 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.9685. Min Act: -0.1700
Data Index: 5528603 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.9373. Min Act: -0.1700
Data Index: 7160924 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.9060. Min Act: -0.1700
Data Index: 781057 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.8748. Min Act: -0.1700
Data Index: 5848539 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.8123. Min Act: -0.1700
Data Index: 5855585 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.8123. Min Act: -0.1700
Data Index: 5855582 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.7498. Min Act: -0.1700
Data Index: 5747541 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.7498. Min Act: -0.1700
Data Index: 7623737 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.7498. Min Act: -0.1700
Data Index: 1981913 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.6873. Min Act: -0.1700
Data Index: 3434335 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9060. Min Range: -7.9060
Max Act: 6.7185. Min Act: -0.1700
Data Index: 5247573 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19