Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2802. Min Range: -4.2802
Max Act: 4.2802. Min Act: -0.1700
Data Index: 3696040 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2802. Min Range: -4.2802
Max Act: 4.0927. Min Act: -0.1700
Data Index: 2293475 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2802. Min Range: -4.2802
Max Act: 4.0614. Min Act: -0.1700
Data Index: 6652119 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.9989. Min Act: -0.1700
Data Index: 5195113 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.9677. Min Act: -0.1700
Data Index: 799361 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.9677. Min Act: -0.1700
Data Index: 4783028 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.9051. Min Act: -0.1700
Data Index: 910070 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 5996798 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 8317838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 1072435 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 1267874 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 3661805 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 1457368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 8515600 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8739. Min Act: -0.1700
Data Index: 5723745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.8426. Min Act: -0.1700
Data Index: 2661931 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.7800. Min Act: -0.1700
Data Index: 5733984 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.7800. Min Act: -0.1700
Data Index: 2827911 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.7800. Min Act: -0.1700
Data Index: 2604426 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2802. Min Range: -4.2802
Max Act: 3.7800. Min Act: -0.1700
Data Index: 5952288 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19