Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5717 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.5173. Min Act: -0.1700
Data Index: 1214609 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.3298. Min Act: -0.1700
Data Index: 8056676 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.3610. Min Act: -0.1700
Data Index: 4384394 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2673. Min Act: -0.1700
Data Index: 5055700 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2673. Min Act: -0.1700
Data Index: 8116397 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2673. Min Act: -0.1700
Data Index: 8044005 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1733283 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2048. Min Act: -0.1700
Data Index: 33943 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2360. Min Act: -0.1700
Data Index: 4054209 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2360. Min Act: -0.1700
Data Index: 4100860 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2048. Min Act: -0.1700
Data Index: 2969753 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2360. Min Act: -0.1700
Data Index: 613973 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2048. Min Act: -0.1700
Data Index: 5907526 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.1735. Min Act: -0.1700
Data Index: 4507993 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.2048. Min Act: -0.1700
Data Index: 3563688 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.1735. Min Act: -0.1700
Data Index: 556096 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.1735. Min Act: -0.1700
Data Index: 949110 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.1423. Min Act: -0.1700
Data Index: 6530159 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.1110. Min Act: -0.1700
Data Index: 5909018 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5173. Min Range: -5.5173
Max Act: 5.1423. Min Act: -0.1700
Data Index: 3728159 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19