Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.1941. Min Act: -0.1700
Data Index: 4014108 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.1003. Min Act: -0.1700
Data Index: 6331601 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0691. Min Act: -0.1700
Data Index: 8557465 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0691. Min Act: -0.1700
Data Index: 5830731 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1941. Min Range: -5.1941
Max Act: 5.0066. Min Act: -0.1700
Data Index: 1852552 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 6401741 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9753. Min Act: -0.1700
Data Index: 6639997 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.9441. Min Act: -0.1700
Data Index: 2991126 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.8816. Min Act: -0.1700
Data Index: 8757284 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.8191. Min Act: -0.1700
Data Index: 4539712 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.8503. Min Act: -0.1700
Data Index: 7705016 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.8191. Min Act: -0.1700
Data Index: 6976904 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.8191. Min Act: -0.1700
Data Index: 1996396 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.8191. Min Act: -0.1700
Data Index: 8513887 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.7566. Min Act: -0.1700
Data Index: 6039834 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.7253. Min Act: -0.1700
Data Index: 7020805 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.7566. Min Act: -0.1700
Data Index: 7549894 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.7253. Min Act: -0.1700
Data Index: 769105 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.7253. Min Act: -0.1700
Data Index: 5347267 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1941. Min Range: -5.1941
Max Act: 4.7253. Min Act: -0.1700
Data Index: 4864169 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19