Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1577 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1547. Min Range: -5.1547
Max Act: 5.1547. Min Act: -0.1700
Data Index: 8824395 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1547. Min Range: -5.1547
Max Act: 5.1234. Min Act: -0.1700
Data Index: 1390308 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1547. Min Range: -5.1547
Max Act: 5.1234. Min Act: -0.1700
Data Index: 397679 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1547. Min Range: -5.1547
Max Act: 5.0609. Min Act: -0.1700
Data Index: 5040164 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1547. Min Range: -5.1547
Max Act: 5.0297. Min Act: -0.1700
Data Index: 3467074 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9984. Min Act: -0.1700
Data Index: 4964873 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9672. Min Act: -0.1700
Data Index: 3474485 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5960638 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9359. Min Act: -0.1700
Data Index: 6780565 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9047. Min Act: -0.1700
Data Index: 5446672 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9359. Min Act: -0.1700
Data Index: 895783 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9047. Min Act: -0.1700
Data Index: 1103604 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9047. Min Act: -0.1700
Data Index: 426940 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.9047. Min Act: -0.1700
Data Index: 3484486 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.8734. Min Act: -0.1700
Data Index: 6144711 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.8734. Min Act: -0.1700
Data Index: 1815286 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.8422. Min Act: -0.1700
Data Index: 2535176 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.8422. Min Act: -0.1700
Data Index: 5631655 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.8734. Min Act: -0.1700
Data Index: 1955793 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1547. Min Range: -5.1547
Max Act: 4.8422. Min Act: -0.1700
Data Index: 781364 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19