Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.4682. Min Act: -0.1700
Data Index: 4050859 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.4370. Min Act: -0.1700
Data Index: 7516370 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.4370. Min Act: -0.1700
Data Index: 2154113 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.4682. Min Act: -0.1700
Data Index: 2402063 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.4057. Min Act: -0.1700
Data Index: 5081596 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3745. Min Act: -0.1700
Data Index: 131428 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7735435 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3120. Min Act: -0.1700
Data Index: 3598978 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3432. Min Act: -0.1700
Data Index: 651586 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3745. Min Act: -0.1700
Data Index: 2071078 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3120. Min Act: -0.1700
Data Index: 4628467 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.2807. Min Act: -0.1700
Data Index: 3053336 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3120. Min Act: -0.1700
Data Index: 6169970 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3120. Min Act: -0.1700
Data Index: 7836527 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3120. Min Act: -0.1700
Data Index: 1561384 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.3120. Min Act: -0.1700
Data Index: 6961564 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.2495. Min Act: -0.1700
Data Index: 666384 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.2807. Min Act: -0.1700
Data Index: 5950150 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.2807. Min Act: -0.1700
Data Index: 3355405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4682. Min Range: -5.4682
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2885189 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19