Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1624 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.7266. Min Act: -0.1700
Data Index: 5892949 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.7106. Min Act: -0.1700
Data Index: 1936071 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6786. Min Act: -0.1700
Data Index: 3468098 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6786. Min Act: -0.1700
Data Index: 8021989 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6466. Min Act: -0.1700
Data Index: 81581 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6305. Min Act: -0.1700
Data Index: 2779814 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6305. Min Act: -0.1700
Data Index: 7967763 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6305. Min Act: -0.1700
Data Index: 3093989 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6305. Min Act: -0.1700
Data Index: 3196012 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.6305. Min Act: -0.1700
Data Index: 4696795 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 3559778 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5983. Min Act: -0.1700
Data Index: 5338130 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5822. Min Act: -0.1700
Data Index: 5082393 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5822. Min Act: -0.1700
Data Index: 8134416 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5661. Min Act: -0.1700
Data Index: 8225510 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5661. Min Act: -0.1700
Data Index: 4947912 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5500. Min Act: -0.1700
Data Index: 6382042 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5661. Min Act: -0.1700
Data Index: 3723806 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5500. Min Act: -0.1700
Data Index: 3671045 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7266. Min Range: -2.7266
Max Act: 2.5338. Min Act: -0.1700
Data Index: 152542 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19