Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 780 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.8758. Min Act: -0.1700
Data Index: 3259372 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.4696. Min Act: -0.1700
Data Index: 4002283 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.2821. Min Act: -0.1700
Data Index: 4614353 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.1883. Min Act: -0.1700
Data Index: 6208609 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.1571. Min Act: -0.1700
Data Index: 4674884 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.1883. Min Act: -0.1700
Data Index: 3465364 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.1258. Min Act: -0.1700
Data Index: 2125229 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0633. Min Act: -0.1700
Data Index: 2119755 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0633. Min Act: -0.1700
Data Index: 7213055 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0633. Min Act: -0.1700
Data Index: 1540431 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0633. Min Act: -0.1700
Data Index: 8781311 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0633. Min Act: -0.1700
Data Index: 7006111 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0321. Min Act: -0.1700
Data Index: 1734236 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0321. Min Act: -0.1700
Data Index: 8553702 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8758. Min Range: -6.8758
Max Act: 6.0008. Min Act: -0.1700
Data Index: 7519029 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8758. Min Range: -6.8758
Max Act: 5.9383. Min Act: -0.1700
Data Index: 1001463 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8758. Min Range: -6.8758
Max Act: 5.9696. Min Act: -0.1700
Data Index: 8632755 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8758. Min Range: -6.8758
Max Act: 5.9696. Min Act: -0.1700
Data Index: 4872476 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8758. Min Range: -6.8758
Max Act: 5.9383. Min Act: -0.1700
Data Index: 6290135 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8758. Min Range: -6.8758
Max Act: 5.9383. Min Act: -0.1700
Data Index: 8811149 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19