Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9341. Min Range: -9.9341
Max Act: 9.9341. Min Act: -0.1700
Data Index: 4021567 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9341. Min Range: -9.9341
Max Act: 9.1841. Min Act: -0.1700
Data Index: 3040908 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9341. Min Range: -9.9341
Max Act: 9.1216. Min Act: -0.1700
Data Index: 95920 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9341. Min Range: -9.9341
Max Act: 9.1216. Min Act: -0.1700
Data Index: 1724668 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.9966. Min Act: -0.1700
Data Index: 1243391 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.8716. Min Act: -0.1700
Data Index: 6741361 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.8716. Min Act: -0.1700
Data Index: 198260 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.9341. Min Act: -0.1700
Data Index: 6217090 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.7466. Min Act: -0.1700
Data Index: 173047 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.8091. Min Act: -0.1700
Data Index: 1454950 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.6841. Min Act: -0.1700
Data Index: 2666473 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.6841. Min Act: -0.1700
Data Index: 7357562 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.7466. Min Act: -0.1700
Data Index: 2960031 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.6841. Min Act: -0.1700
Data Index: 4344236 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.6216. Min Act: -0.1700
Data Index: 1642395 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.6216. Min Act: -0.1700
Data Index: 887856 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.6216. Min Act: -0.1700
Data Index: 4271708 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.5591. Min Act: -0.1700
Data Index: 5553238 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.5591. Min Act: -0.1700
Data Index: 4577106 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9341. Min Range: -9.9341
Max Act: 8.4966. Min Act: -0.1700
Data Index: 4208569 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19