Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0295. Min Range: -12.0295
Max Act: 12.0295. Min Act: -0.1700
Data Index: 8596320 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0295. Min Range: -12.0295
Max Act: 11.7795. Min Act: -0.1700
Data Index: 8354354 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0295. Min Range: -12.0295
Max Act: 11.2170. Min Act: -0.1700
Data Index: 8434398 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0295. Min Range: -12.0295
Max Act: 11.0295. Min Act: -0.1700
Data Index: 1545878 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.9045. Min Act: -0.1700
Data Index: 1132130 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.7795. Min Act: -0.1700
Data Index: 2562982 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.7795. Min Act: -0.1700
Data Index: 5690392 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.6545. Min Act: -0.1700
Data Index: 7971477 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.7170. Min Act: -0.1700
Data Index: 5905766 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5920. Min Act: -0.1700
Data Index: 1124687 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5920. Min Act: -0.1700
Data Index: 2378345 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5920. Min Act: -0.1700
Data Index: 4708325 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5920. Min Act: -0.1700
Data Index: 4268314 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.6545. Min Act: -0.1700
Data Index: 2643741 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5920. Min Act: -0.1700
Data Index: 5804001 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5920. Min Act: -0.1700
Data Index: 449934 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5295. Min Act: -0.1700
Data Index: 2797609 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5295. Min Act: -0.1700
Data Index: 5703334 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5295. Min Act: -0.1700
Data Index: 8147729 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0295. Min Range: -12.0295
Max Act: 10.5295. Min Act: -0.1700
Data Index: 3590898 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19