Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2072 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4724. Min Range: -8.4724
Max Act: 8.4724. Min Act: -0.1700
Data Index: 1305264 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4724. Min Range: -8.4724
Max Act: 8.3474. Min Act: -0.1700
Data Index: 7759325 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4724. Min Range: -8.4724
Max Act: 8.0974. Min Act: -0.1700
Data Index: 329132 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.9724. Min Act: -0.1700
Data Index: 261995 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.9099. Min Act: -0.1700
Data Index: 8751979 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.9099. Min Act: -0.1700
Data Index: 261977 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7849. Min Act: -0.1700
Data Index: 3386621 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.8474. Min Act: -0.1700
Data Index: 1081070 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.8474. Min Act: -0.1700
Data Index: 6329733 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7849. Min Act: -0.1700
Data Index: 4132986 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7849. Min Act: -0.1700
Data Index: 261974 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7849. Min Act: -0.1700
Data Index: 7387241 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7849. Min Act: -0.1700
Data Index: 6854548 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7537. Min Act: -0.1700
Data Index: 3527001 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7537. Min Act: -0.1700
Data Index: 1612781 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7537. Min Act: -0.1700
Data Index: 376957 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7849. Min Act: -0.1700
Data Index: 1406734 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7537. Min Act: -0.1700
Data Index: 6204220 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7224. Min Act: -0.1700
Data Index: 261986 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4724. Min Range: -8.4724
Max Act: 7.7224. Min Act: -0.1700
Data Index: 2376332 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19