Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4751 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0636. Min Range: -3.0636
Max Act: 3.0636. Min Act: -0.1700
Data Index: 2341597 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0636. Min Range: -3.0636
Max Act: 3.0162. Min Act: -0.1700
Data Index: 7463830 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.9213. Min Act: -0.1700
Data Index: 6875291 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.9371. Min Act: -0.1700
Data Index: 727167 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.9213. Min Act: -0.1700
Data Index: 3061747 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.9054. Min Act: -0.1700
Data Index: 7392340 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8896. Min Act: -0.1700
Data Index: 6454242 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8896. Min Act: -0.1700
Data Index: 3504218 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8737. Min Act: -0.1700
Data Index: 4756845 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8578. Min Act: -0.1700
Data Index: 3250044 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8896. Min Act: -0.1700
Data Index: 7808700 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8419. Min Act: -0.1700
Data Index: 3460494 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8578. Min Act: -0.1700
Data Index: 1002293 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8260. Min Act: -0.1700
Data Index: 5254543 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8578. Min Act: -0.1700
Data Index: 7314736 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8260. Min Act: -0.1700
Data Index: 816756 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8419. Min Act: -0.1700
Data Index: 5850331 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8260. Min Act: -0.1700
Data Index: 5424685 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.8101. Min Act: -0.1700
Data Index: 5444569 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0636. Min Range: -3.0636
Max Act: 2.7942. Min Act: -0.1700
Data Index: 5003155 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19