Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3416 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.9100. Min Act: -0.1700
Data Index: 447693 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.7225. Min Act: -0.1700
Data Index: 2332212 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.2850. Min Act: -0.1700
Data Index: 5242406 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.2850. Min Act: -0.1700
Data Index: 7583342 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.2225. Min Act: -0.1700
Data Index: 4996066 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.2225. Min Act: -0.1700
Data Index: 8394976 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.1600. Min Act: -0.1700
Data Index: 6185383 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.1600. Min Act: -0.1700
Data Index: 4075586 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.0975. Min Act: -0.1700
Data Index: 3921716 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.0350. Min Act: -0.1700
Data Index: 3902529 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9100. Min Range: -9.9100
Max Act: 9.0350. Min Act: -0.1700
Data Index: 4968639 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.9100. Min Act: -0.1700
Data Index: 3768633 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.9100. Min Act: -0.1700
Data Index: 7980173 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 2311025 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 7484840 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 3529121 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 3172056 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 2832071 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 1775798 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9100. Min Range: -9.9100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 7213855 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19