Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4326 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 3825363 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.9510. Min Act: -0.1700
Data Index: 5751152 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.9352. Min Act: -0.1700
Data Index: 2670738 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.9510. Min Act: -0.1700
Data Index: 2695270 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8717. Min Act: -0.1700
Data Index: 2695269 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8876. Min Act: -0.1700
Data Index: 3742167 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8717. Min Act: -0.1700
Data Index: 925509 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8717. Min Act: -0.1700
Data Index: 7032762 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8559. Min Act: -0.1700
Data Index: 5504212 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8559. Min Act: -0.1700
Data Index: 3264408 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8559. Min Act: -0.1700
Data Index: 4104346 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8559. Min Act: -0.1700
Data Index: 1172432 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8400. Min Act: -0.1700
Data Index: 2275528 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8400. Min Act: -0.1700
Data Index: 4541231 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.8400. Min Act: -0.1700
Data Index: 6270661 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.7922. Min Act: -0.1700
Data Index: 6519017 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.7922. Min Act: -0.1700
Data Index: 8819086 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.7763. Min Act: -0.1700
Data Index: 1108824 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.7922. Min Act: -0.1700
Data Index: 2791993 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1562. Min Range: -3.1562
Max Act: 2.7763. Min Act: -0.1700
Data Index: 303627 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19