Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.7117. Min Act: -0.1700
Data Index: 2314660 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.5242. Min Act: -0.1700
Data Index: 6895721 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.5242. Min Act: -0.1700
Data Index: 7793905 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.5242. Min Act: -0.1700
Data Index: 2487371 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.4929. Min Act: -0.1700
Data Index: 8803391 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.4617. Min Act: -0.1700
Data Index: 1456979 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.4617. Min Act: -0.1700
Data Index: 2108419 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.3992. Min Act: -0.1700
Data Index: 2139375 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.3679. Min Act: -0.1700
Data Index: 2782010 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 1100572 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2429. Min Act: -0.1700
Data Index: 5812846 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 2304873 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1804. Min Act: -0.1700
Data Index: 893748 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 4673106 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1804. Min Act: -0.1700
Data Index: 5591922 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1804. Min Act: -0.1700
Data Index: 5155713 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1804. Min Act: -0.1700
Data Index: 1116119 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1492. Min Act: -0.1700
Data Index: 5543458 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1492. Min Act: -0.1700
Data Index: 4437015 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1179. Min Act: -0.1700
Data Index: 491054 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19