Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.2933. Min Act: -0.1700
Data Index: 4596260 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.1683. Min Act: -0.1700
Data Index: 5150082 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.2308. Min Act: -0.1700
Data Index: 1322959 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.2308. Min Act: -0.1700
Data Index: 5749850 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.1683. Min Act: -0.1700
Data Index: 3269214 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.1058. Min Act: -0.1700
Data Index: 4425800 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.1058. Min Act: -0.1700
Data Index: 4425798 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2933. Min Range: -10.2933
Max Act: 10.1058. Min Act: -0.1700
Data Index: 5150083 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.9808. Min Act: -0.1700
Data Index: 4596261 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.9183. Min Act: -0.1700
Data Index: 1322960 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.9183. Min Act: -0.1700
Data Index: 3269216 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.7933. Min Act: -0.1700
Data Index: 4425799 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.7933. Min Act: -0.1700
Data Index: 3688052 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.7308. Min Act: -0.1700
Data Index: 5749852 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.7933. Min Act: -0.1700
Data Index: 5749851 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.8558. Min Act: -0.1700
Data Index: 7085497 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.7308. Min Act: -0.1700
Data Index: 8245158 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.6683. Min Act: -0.1700
Data Index: 3473 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.6683. Min Act: -0.1700
Data Index: 5491956 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2933. Min Range: -10.2933
Max Act: 9.6058. Min Act: -0.1700
Data Index: 783015 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19