Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0458. Min Range: -4.0458
Max Act: 4.0458. Min Act: -0.1700
Data Index: 2935854 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0458. Min Range: -4.0458
Max Act: 4.0458. Min Act: -0.1700
Data Index: 1133014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9520. Min Act: -0.1700
Data Index: 4312479 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9520. Min Act: -0.1700
Data Index: 7140120 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9520. Min Act: -0.1700
Data Index: 6134903 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9208. Min Act: -0.1700
Data Index: 6513692 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9208. Min Act: -0.1700
Data Index: 4371810 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9208. Min Act: -0.1700
Data Index: 2191123 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9208. Min Act: -0.1700
Data Index: 1035138 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9520. Min Act: -0.1700
Data Index: 3182631 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8895. Min Act: -0.1700
Data Index: 4669619 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8582. Min Act: -0.1700
Data Index: 8803304 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8895. Min Act: -0.1700
Data Index: 8742927 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8895. Min Act: -0.1700
Data Index: 7892113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9208. Min Act: -0.1700
Data Index: 7670556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.9208. Min Act: -0.1700
Data Index: 5333769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8895. Min Act: -0.1700
Data Index: 5003270 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8895. Min Act: -0.1700
Data Index: 2116249 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8895. Min Act: -0.1700
Data Index: 7062558 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0458. Min Range: -4.0458
Max Act: 3.8582. Min Act: -0.1700
Data Index: 1760671 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19