Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.6749. Min Act: -0.1700
Data Index: 6308666 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.5810. Min Act: -0.1700
Data Index: 6510859 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.5966. Min Act: -0.1700
Data Index: 6696602 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.5966. Min Act: -0.1700
Data Index: 3382358 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.5340. Min Act: -0.1700
Data Index: 3079078 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.5184. Min Act: -0.1700
Data Index: 1649556 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.5027. Min Act: -0.1700
Data Index: 967539 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.4087. Min Act: -0.1700
Data Index: 3363708 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.3930. Min Act: -0.1700
Data Index: 1368664 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.3773. Min Act: -0.1700
Data Index: 4831032 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.3773. Min Act: -0.1700
Data Index: 4507538 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.3303. Min Act: -0.1700
Data Index: 5148126 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.3303. Min Act: -0.1700
Data Index: 7072865 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2675. Min Act: -0.1700
Data Index: 548668 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2989. Min Act: -0.1700
Data Index: 3481560 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2675. Min Act: -0.1700
Data Index: 691871 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2675. Min Act: -0.1700
Data Index: 5077927 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2518. Min Act: -0.1700
Data Index: 2340213 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2675. Min Act: -0.1700
Data Index: 5015225 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6749. Min Range: -3.6749
Max Act: 3.2360. Min Act: -0.1700
Data Index: 6303160 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19