Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.4682. Min Act: -0.1700
Data Index: 962600 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.4369. Min Act: -0.1700
Data Index: 4103185 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.4057. Min Act: -0.1700
Data Index: 4834699 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 1710553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 2285118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 5890736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 2267388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 5284368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 4784792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 2440636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 573644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 5329862 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 8316722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 6055776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3744. Min Act: -0.1700
Data Index: 2312487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.2494. Min Act: -0.1700
Data Index: 144724 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.3119. Min Act: -0.1700
Data Index: 872643 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.2807. Min Act: -0.1700
Data Index: 863606 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.2494. Min Act: -0.1700
Data Index: 7579582 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4682. Min Range: -4.4682
Max Act: 4.2182. Min Act: -0.1700
Data Index: 6315378 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19