Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1057 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.3947. Min Act: -0.1700
Data Index: 5044470 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.3635. Min Act: -0.1700
Data Index: 1695113 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.2697. Min Act: -0.1700
Data Index: 3502152 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.2385. Min Act: -0.1700
Data Index: 6224357 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.2385. Min Act: -0.1700
Data Index: 7341305 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.1447. Min Act: -0.1700
Data Index: 730173 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0509. Min Act: -0.1700
Data Index: 285514 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0197. Min Act: -0.1700
Data Index: 6864084 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0509. Min Act: -0.1700
Data Index: 6670101 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0197. Min Act: -0.1700
Data Index: 4673059 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0197. Min Act: -0.1700
Data Index: 5947903 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0197. Min Act: -0.1700
Data Index: 6362530 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3947. Min Range: -4.3947
Max Act: 4.0197. Min Act: -0.1700
Data Index: 3896798 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.9884. Min Act: -0.1700
Data Index: 5606919 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.9884. Min Act: -0.1700
Data Index: 6567264 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.9572. Min Act: -0.1700
Data Index: 1886992 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.9259. Min Act: -0.1700
Data Index: 2925814 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.8946. Min Act: -0.1700
Data Index: 8719620 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.8634. Min Act: -0.1700
Data Index: 6155406 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3947. Min Range: -4.3947
Max Act: 3.8321. Min Act: -0.1700
Data Index: 4121183 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19