Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2930. Min Range: -6.2930
Max Act: 6.2930. Min Act: -0.1700
Data Index: 5078260 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2930. Min Range: -6.2930
Max Act: 6.2305. Min Act: -0.1700
Data Index: 3298884 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2930. Min Range: -6.2930
Max Act: 6.1055. Min Act: -0.1700
Data Index: 3142981 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2930. Min Range: -6.2930
Max Act: 6.0117. Min Act: -0.1700
Data Index: 2260027 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.9805. Min Act: -0.1700
Data Index: 7223220 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.9492. Min Act: -0.1700
Data Index: 1310118 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.9180. Min Act: -0.1700
Data Index: 3257447 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.8555. Min Act: -0.1700
Data Index: 8117806 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.8555. Min Act: -0.1700
Data Index: 4650015 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.7930. Min Act: -0.1700
Data Index: 6420776 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.7305. Min Act: -0.1700
Data Index: 5992980 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.7617. Min Act: -0.1700
Data Index: 7792072 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.7305. Min Act: -0.1700
Data Index: 5154612 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.7305. Min Act: -0.1700
Data Index: 6955117 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.6992. Min Act: -0.1700
Data Index: 1773082 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.6992. Min Act: -0.1700
Data Index: 2877902 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.6367. Min Act: -0.1700
Data Index: 4965573 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.6680. Min Act: -0.1700
Data Index: 7950085 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.6055. Min Act: -0.1700
Data Index: 2600941 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2930. Min Range: -6.2930
Max Act: 5.6367. Min Act: -0.1700
Data Index: 7183677 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19