Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8224. Min Range: -8.8224
Max Act: 8.8224. Min Act: -0.1700
Data Index: 738770 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8224. Min Range: -8.8224
Max Act: 8.2599. Min Act: -0.1700
Data Index: 4841863 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.8224. Min Act: -0.1700
Data Index: 7574737 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.7911. Min Act: -0.1700
Data Index: 8150421 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.7599. Min Act: -0.1700
Data Index: 3877075 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.7286. Min Act: -0.1700
Data Index: 6771282 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.5411. Min Act: -0.1700
Data Index: 5403628 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.4161. Min Act: -0.1700
Data Index: 6838397 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.3849. Min Act: -0.1700
Data Index: 4988297 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.3849. Min Act: -0.1700
Data Index: 6904170 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.3536. Min Act: -0.1700
Data Index: 7474567 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.3224. Min Act: -0.1700
Data Index: 4710243 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.3224. Min Act: -0.1700
Data Index: 5604338 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 497493 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 3953249 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 8115498 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 4575673 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.2599. Min Act: -0.1700
Data Index: 6187815 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.1974. Min Act: -0.1700
Data Index: 2302106 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8224. Min Range: -8.8224
Max Act: 7.1661. Min Act: -0.1700
Data Index: 7708666 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19