Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2117. Min Range: -8.2117
Max Act: 8.2117. Min Act: -0.1700
Data Index: 4667363 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7742. Min Act: -0.1700
Data Index: 1241768 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7742. Min Act: -0.1700
Data Index: 7714620 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7742. Min Act: -0.1700
Data Index: 2154507 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7742. Min Act: -0.1700
Data Index: 2111457 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7742. Min Act: -0.1700
Data Index: 6927778 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7742. Min Act: -0.1700
Data Index: 6409639 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7117. Min Act: -0.1700
Data Index: 5205372 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.7117. Min Act: -0.1700
Data Index: 7981199 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.6492. Min Act: -0.1700
Data Index: 3891267 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.6492. Min Act: -0.1700
Data Index: 4663774 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.6492. Min Act: -0.1700
Data Index: 2041924 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.6492. Min Act: -0.1700
Data Index: 7813284 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.5867. Min Act: -0.1700
Data Index: 1390976 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.5867. Min Act: -0.1700
Data Index: 947557 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.5554. Min Act: -0.1700
Data Index: 8421775 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.5867. Min Act: -0.1700
Data Index: 4806063 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.6492. Min Act: -0.1700
Data Index: 6466290 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.5867. Min Act: -0.1700
Data Index: 5002123 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2117. Min Range: -8.2117
Max Act: 7.5554. Min Act: -0.1700
Data Index: 1711179 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19