Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1054. Min Range: -5.1054
Max Act: 5.1054. Min Act: -0.1700
Data Index: 8066438 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1054. Min Range: -5.1054
Max Act: 5.0742. Min Act: -0.1700
Data Index: 6034744 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1054. Min Range: -5.1054
Max Act: 5.0117. Min Act: -0.1700
Data Index: 8397280 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9804. Min Act: -0.1700
Data Index: 8199663 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9804. Min Act: -0.1700
Data Index: 5764753 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9179. Min Act: -0.1700
Data Index: 1533525 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9492. Min Act: -0.1700
Data Index: 6980691 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9492. Min Act: -0.1700
Data Index: 5541039 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9179. Min Act: -0.1700
Data Index: 1332847 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8867. Min Act: -0.1700
Data Index: 2405723 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8867. Min Act: -0.1700
Data Index: 7807833 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8867. Min Act: -0.1700
Data Index: 2925482 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8867. Min Act: -0.1700
Data Index: 3321929 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8554. Min Act: -0.1700
Data Index: 8397285 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8242. Min Act: -0.1700
Data Index: 7340081 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8242. Min Act: -0.1700
Data Index: 1926122 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8242. Min Act: -0.1700
Data Index: 1260881 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8242. Min Act: -0.1700
Data Index: 440686 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7929. Min Act: -0.1700
Data Index: 1462489 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7929. Min Act: -0.1700
Data Index: 2359408 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19