Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1764. Min Range: -4.1764
Max Act: 4.1764. Min Act: -0.1700
Data Index: 4297542 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.9888. Min Act: -0.1700
Data Index: 7537626 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8950. Min Act: -0.1700
Data Index: 3434839 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8950. Min Act: -0.1700
Data Index: 149940 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8950. Min Act: -0.1700
Data Index: 8806513 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8638. Min Act: -0.1700
Data Index: 1638541 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8638. Min Act: -0.1700
Data Index: 7198222 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8325. Min Act: -0.1700
Data Index: 2481724 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8012. Min Act: -0.1700
Data Index: 2991479 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8325. Min Act: -0.1700
Data Index: 2617016 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8325. Min Act: -0.1700
Data Index: 5506652 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8325. Min Act: -0.1700
Data Index: 4089060 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8325. Min Act: -0.1700
Data Index: 6107563 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8638. Min Act: -0.1700
Data Index: 3320929 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8012. Min Act: -0.1700
Data Index: 1932637 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.8012. Min Act: -0.1700
Data Index: 8346715 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.7856. Min Act: -0.1700
Data Index: 7111152 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.7856. Min Act: -0.1700
Data Index: 343518 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.7856. Min Act: -0.1700
Data Index: 4307680 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1764. Min Range: -4.1764
Max Act: 3.7856. Min Act: -0.1700
Data Index: 8019352 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19