Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4266 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.4154. Min Act: -0.1700
Data Index: 5056741 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.4154. Min Act: -0.1700
Data Index: 7606611 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.3529. Min Act: -0.1700
Data Index: 3250941 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.3216. Min Act: -0.1700
Data Index: 6685091 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2904. Min Act: -0.1700
Data Index: 1380079 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2904. Min Act: -0.1700
Data Index: 3392832 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2904. Min Act: -0.1700
Data Index: 8199551 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2904. Min Act: -0.1700
Data Index: 5565718 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2591. Min Act: -0.1700
Data Index: 4285004 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2279. Min Act: -0.1700
Data Index: 4557736 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2279. Min Act: -0.1700
Data Index: 635497 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2279. Min Act: -0.1700
Data Index: 1264847 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.2279. Min Act: -0.1700
Data Index: 3345014 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1966. Min Act: -0.1700
Data Index: 2744711 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1966. Min Act: -0.1700
Data Index: 414892 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1966. Min Act: -0.1700
Data Index: 977736 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1966. Min Act: -0.1700
Data Index: 3645542 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1654. Min Act: -0.1700
Data Index: 121555 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1654. Min Act: -0.1700
Data Index: 1228432 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4154. Min Range: -5.4154
Max Act: 5.1341. Min Act: -0.1700
Data Index: 1145862 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19