Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 132 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.4651. Min Act: -0.1700
Data Index: 3072842 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.2151. Min Act: -0.1700
Data Index: 1820453 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.1839. Min Act: -0.1700
Data Index: 6120991 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0901. Min Act: -0.1700
Data Index: 1507874 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0901. Min Act: -0.1700
Data Index: 872412 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0589. Min Act: -0.1700
Data Index: 8095493 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0276. Min Act: -0.1700
Data Index: 8503287 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0589. Min Act: -0.1700
Data Index: 916783 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9651. Min Act: -0.1700
Data Index: 1742695 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0276. Min Act: -0.1700
Data Index: 7008119 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9964. Min Act: -0.1700
Data Index: 3872086 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4651. Min Range: -5.4651
Max Act: 5.0276. Min Act: -0.1700
Data Index: 7638803 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9964. Min Act: -0.1700
Data Index: 3006227 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9651. Min Act: -0.1700
Data Index: 4375862 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9964. Min Act: -0.1700
Data Index: 5176974 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9651. Min Act: -0.1700
Data Index: 4130287 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.9339. Min Act: -0.1700
Data Index: 3134978 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.8714. Min Act: -0.1700
Data Index: 5144598 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.8401. Min Act: -0.1700
Data Index: 5240238 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4651. Min Range: -5.4651
Max Act: 4.8714. Min Act: -0.1700
Data Index: 7896748 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19