Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3528. Min Range: -4.3528
Max Act: 4.3528. Min Act: -0.1700
Data Index: 7024822 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3528. Min Range: -4.3528
Max Act: 4.2591. Min Act: -0.1700
Data Index: 1019183 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3528. Min Range: -4.3528
Max Act: 4.1341. Min Act: -0.1700
Data Index: 1031094 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3528. Min Range: -4.3528
Max Act: 4.0090. Min Act: -0.1700
Data Index: 7379323 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3528. Min Range: -4.3528
Max Act: 4.0090. Min Act: -0.1700
Data Index: 7348731 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3528. Min Range: -4.3528
Max Act: 4.0090. Min Act: -0.1700
Data Index: 5259859 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.9778. Min Act: -0.1700
Data Index: 291091 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.9465. Min Act: -0.1700
Data Index: 7615597 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.9465. Min Act: -0.1700
Data Index: 6245193 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.9153. Min Act: -0.1700
Data Index: 8250022 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.9153. Min Act: -0.1700
Data Index: 4731395 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.9153. Min Act: -0.1700
Data Index: 2001288 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 7357013 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 3348413 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 2413768 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 5913541 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 4684757 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 5818024 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8840. Min Act: -0.1700
Data Index: 1013575 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3528. Min Range: -4.3528
Max Act: 3.8684. Min Act: -0.1700
Data Index: 5837064 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19