Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1548 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.2389. Min Act: -0.1700
Data Index: 4929093 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.2389. Min Act: -0.1700
Data Index: 5004227 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.1764. Min Act: -0.1700
Data Index: 8067824 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.0514. Min Act: -0.1700
Data Index: 4989999 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.0514. Min Act: -0.1700
Data Index: 4990002 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9889. Min Act: -0.1700
Data Index: 5987956 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.0514. Min Act: -0.1700
Data Index: 97050 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9889. Min Act: -0.1700
Data Index: 8067822 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9889. Min Act: -0.1700
Data Index: 2289711 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2389. Min Range: -14.2389
Max Act: 14.0514. Min Act: -0.1700
Data Index: 8274878 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9889. Min Act: -0.1700
Data Index: 5987954 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9264. Min Act: -0.1700
Data Index: 8653808 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9264. Min Act: -0.1700
Data Index: 8115851 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9264. Min Act: -0.1700
Data Index: 8495907 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9889. Min Act: -0.1700
Data Index: 8583492 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.9264. Min Act: -0.1700
Data Index: 8581825 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.8639. Min Act: -0.1700
Data Index: 5495028 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.8014. Min Act: -0.1700
Data Index: 8067825 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.8639. Min Act: -0.1700
Data Index: 1645857 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2389. Min Range: -14.2389
Max Act: 13.8014. Min Act: -0.1700
Data Index: 2289729 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19