Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3999. Min Range: -8.3999
Max Act: 8.3999. Min Act: -0.1700
Data Index: 2963520 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3999. Min Range: -8.3999
Max Act: 8.3999. Min Act: -0.1700
Data Index: 1383216 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3999. Min Range: -8.3999
Max Act: 8.1499. Min Act: -0.1700
Data Index: 1233318 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3999. Min Range: -8.3999
Max Act: 8.0874. Min Act: -0.1700
Data Index: 6378230 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3999. Min Range: -8.3999
Max Act: 8.0249. Min Act: -0.1700
Data Index: 5537074 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3999. Min Range: -8.3999
Max Act: 8.0249. Min Act: -0.1700
Data Index: 2771311 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.9624. Min Act: -0.1700
Data Index: 506002 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8999. Min Act: -0.1700
Data Index: 4392470 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.9624. Min Act: -0.1700
Data Index: 465048 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8999. Min Act: -0.1700
Data Index: 2436385 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8999. Min Act: -0.1700
Data Index: 1081484 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.9624. Min Act: -0.1700
Data Index: 4480954 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8999. Min Act: -0.1700
Data Index: 3630295 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8999. Min Act: -0.1700
Data Index: 8240687 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8999. Min Act: -0.1700
Data Index: 5151907 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8374. Min Act: -0.1700
Data Index: 5474215 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8374. Min Act: -0.1700
Data Index: 4015121 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8374. Min Act: -0.1700
Data Index: 5192555 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8374. Min Act: -0.1700
Data Index: 6815729 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3999. Min Range: -8.3999
Max Act: 7.8374. Min Act: -0.1700
Data Index: 3310459 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19