Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1481 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.2058. Min Act: -0.1700
Data Index: 3966499 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1901. Min Act: -0.1700
Data Index: 7185583 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1901. Min Act: -0.1700
Data Index: 1201180 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.2058. Min Act: -0.1700
Data Index: 2591446 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1429. Min Act: -0.1700
Data Index: 5122654 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1429. Min Act: -0.1700
Data Index: 6821953 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1271. Min Act: -0.1700
Data Index: 1794283 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1271. Min Act: -0.1700
Data Index: 8018580 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1114. Min Act: -0.1700
Data Index: 2901759 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0799. Min Act: -0.1700
Data Index: 2507584 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0956. Min Act: -0.1700
Data Index: 5229043 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0956. Min Act: -0.1700
Data Index: 4648158 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.1114. Min Act: -0.1700
Data Index: 4648160 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0641. Min Act: -0.1700
Data Index: 7006691 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0641. Min Act: -0.1700
Data Index: 6497513 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0641. Min Act: -0.1700
Data Index: 8167927 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0799. Min Act: -0.1700
Data Index: 2817853 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0483. Min Act: -0.1700
Data Index: 6588866 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0325. Min Act: -0.1700
Data Index: 4278824 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2058. Min Range: -3.2058
Max Act: 3.0325. Min Act: -0.1700
Data Index: 5937356 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19