Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.8541. Min Act: -0.1700
Data Index: 6883796 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.8228. Min Act: -0.1700
Data Index: 163925 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.7916. Min Act: -0.1700
Data Index: 3998966 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.7603. Min Act: -0.1700
Data Index: 8209135 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.7603. Min Act: -0.1700
Data Index: 5702369 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.7291. Min Act: -0.1700
Data Index: 3068019 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6666. Min Act: -0.1700
Data Index: 6249774 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6666. Min Act: -0.1700
Data Index: 327992 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 1883224 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 6428046 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 2929667 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 1649705 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6041. Min Act: -0.1700
Data Index: 7507827 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5756745 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5688856 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 3460740 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 2030744 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5229371 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6041. Min Act: -0.1700
Data Index: 3776752 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6041. Min Act: -0.1700
Data Index: 2223755 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19