Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1577 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.5767. Min Act: -0.1700
Data Index: 8007784 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.3892. Min Act: -0.1700
Data Index: 799365 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.3892. Min Act: -0.1700
Data Index: 7854992 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.3267. Min Act: -0.1700
Data Index: 465336 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.3580. Min Act: -0.1700
Data Index: 7115754 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2955. Min Act: -0.1700
Data Index: 7772755 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2642. Min Act: -0.1700
Data Index: 8127617 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2642. Min Act: -0.1700
Data Index: 8255864 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2017. Min Act: -0.1700
Data Index: 2197793 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2017. Min Act: -0.1700
Data Index: 5909921 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2017. Min Act: -0.1700
Data Index: 1637839 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1705. Min Act: -0.1700
Data Index: 4840066 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1705. Min Act: -0.1700
Data Index: 6961439 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.2017. Min Act: -0.1700
Data Index: 7455283 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1705. Min Act: -0.1700
Data Index: 7249943 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1705. Min Act: -0.1699
Data Index: 8309056 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1392. Min Act: -0.1700
Data Index: 6264283 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1392. Min Act: -0.1700
Data Index: 1685767 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1705. Min Act: -0.1700
Data Index: 7980442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5767. Min Range: -5.5767
Max Act: 5.1392. Min Act: -0.1700
Data Index: 2181524 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19