Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 723 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.3682. Min Act: -0.1700
Data Index: 6357431 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2744. Min Act: -0.1700
Data Index: 6039859 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2744. Min Act: -0.1700
Data Index: 1099826 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2744. Min Act: -0.1700
Data Index: 4255938 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2119. Min Act: -0.1700
Data Index: 3190144 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2432. Min Act: -0.1700
Data Index: 8294076 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2744. Min Act: -0.1700
Data Index: 1099825 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2119. Min Act: -0.1700
Data Index: 4585708 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1807. Min Act: -0.1700
Data Index: 7856778 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.2119. Min Act: -0.1700
Data Index: 2830192 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1494. Min Act: -0.1700
Data Index: 5456063 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1807. Min Act: -0.1700
Data Index: 2555931 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1807. Min Act: -0.1700
Data Index: 7032286 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1807. Min Act: -0.1700
Data Index: 4258811 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1182. Min Act: -0.1700
Data Index: 255442 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1494. Min Act: -0.1700
Data Index: 1475906 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1494. Min Act: -0.1700
Data Index: 7745851 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1494. Min Act: -0.1700
Data Index: 7136492 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1494. Min Act: -0.1700
Data Index: 533902 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3682. Min Range: -5.3682
Max Act: 5.1494. Min Act: -0.1700
Data Index: 6675287 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19