Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2665. Min Range: -6.2665
Max Act: 6.2665. Min Act: -0.1700
Data Index: 7939493 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2665. Min Range: -6.2665
Max Act: 6.1727. Min Act: -0.1700
Data Index: 1017676 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.7977. Min Act: -0.1700
Data Index: 4825337 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3713736 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.2040. Min Act: -0.1700
Data Index: 4603039 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0790. Min Act: -0.1700
Data Index: 1606023 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0477. Min Act: -0.1700
Data Index: 5681529 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0790. Min Act: -0.1700
Data Index: 7354044 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0477. Min Act: -0.1700
Data Index: 5115282 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0477. Min Act: -0.1700
Data Index: 926855 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0477. Min Act: -0.1700
Data Index: 8149957 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0477. Min Act: -0.1700
Data Index: 1750772 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1892232 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0165. Min Act: -0.1700
Data Index: 2206373 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2665. Min Range: -6.2665
Max Act: 5.0165. Min Act: -0.1700
Data Index: 4380289 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2665. Min Range: -6.2665
Max Act: 4.9852. Min Act: -0.1700
Data Index: 2054415 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2665. Min Range: -6.2665
Max Act: 4.9852. Min Act: -0.1700
Data Index: 5711675 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2665. Min Range: -6.2665
Max Act: 4.9852. Min Act: -0.1700
Data Index: 4696448 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2665. Min Range: -6.2665
Max Act: 4.9540. Min Act: -0.1700
Data Index: 287321 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2665. Min Range: -6.2665
Max Act: 4.9540. Min Act: -0.1700
Data Index: 7110150 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19