Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.7831. Min Act: -0.1700
Data Index: 2701545 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.5956. Min Act: -0.1700
Data Index: 563147 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.5644. Min Act: -0.1700
Data Index: 6798625 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.4706. Min Act: -0.1700
Data Index: 7080061 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.5019. Min Act: -0.1700
Data Index: 829250 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.4706. Min Act: -0.1700
Data Index: 6991194 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.4394. Min Act: -0.1700
Data Index: 3337272 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.4081. Min Act: -0.1700
Data Index: 855146 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.3769. Min Act: -0.1700
Data Index: 2722655 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.3456. Min Act: -0.1700
Data Index: 6276746 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.3456. Min Act: -0.1700
Data Index: 5266835 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.2831. Min Act: -0.1700
Data Index: 5552154 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.3144. Min Act: -0.1700
Data Index: 1596800 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.2519. Min Act: -0.1700
Data Index: 581988 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.2519. Min Act: -0.1700
Data Index: 806736 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.2519. Min Act: -0.1700
Data Index: 2230317 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.2206. Min Act: -0.1700
Data Index: 5714065 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.2206. Min Act: -0.1700
Data Index: 4724085 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.1894. Min Act: -0.1700
Data Index: 7022011 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7831. Min Range: -5.7831
Max Act: 5.1894. Min Act: -0.1700
Data Index: 5767994 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19