Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.1060. Min Act: -0.1700
Data Index: 3972815 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0748. Min Act: -0.1700
Data Index: 2003904 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0435. Min Act: -0.1700
Data Index: 7959028 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9810. Min Act: -0.1700
Data Index: 2272924 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9497. Min Act: -0.1700
Data Index: 2637322 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9497. Min Act: -0.1700
Data Index: 1448132 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9497. Min Act: -0.1700
Data Index: 1315486 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9497. Min Act: -0.1700
Data Index: 4374366 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9185. Min Act: -0.1700
Data Index: 733524 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9185. Min Act: -0.1700
Data Index: 8018995 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9185. Min Act: -0.1700
Data Index: 7460696 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.9185. Min Act: -0.1700
Data Index: 2791098 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8872. Min Act: -0.1700
Data Index: 4699748 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8872. Min Act: -0.1700
Data Index: 2094744 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8872. Min Act: -0.1700
Data Index: 5294270 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8559. Min Act: -0.1700
Data Index: 5771032 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8872. Min Act: -0.1700
Data Index: 3530559 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8559. Min Act: -0.1700
Data Index: 2133034 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8403. Min Act: -0.1700
Data Index: 4165067 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1060. Min Range: -4.1060
Max Act: 3.8247. Min Act: -0.1700
Data Index: 8804666 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19