Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0005. Min Range: -5.0005
Max Act: 5.0005. Min Act: -0.1700
Data Index: 4228738 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.9068. Min Act: -0.1700
Data Index: 4817954 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.8755. Min Act: -0.1700
Data Index: 1794053 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.8755. Min Act: -0.1700
Data Index: 4693358 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.8443. Min Act: -0.1700
Data Index: 5344111 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7818. Min Act: -0.1700
Data Index: 152110 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1856516 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7505. Min Act: -0.1700
Data Index: 2896610 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7818. Min Act: -0.1700
Data Index: 549614 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7505. Min Act: -0.1700
Data Index: 3786330 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7193. Min Act: -0.1700
Data Index: 4249578 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7193. Min Act: -0.1700
Data Index: 1338810 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.7193. Min Act: -0.1700
Data Index: 2723611 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6880. Min Act: -0.1700
Data Index: 8133871 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6880. Min Act: -0.1700
Data Index: 6860670 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6880. Min Act: -0.1700
Data Index: 2395908 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6880. Min Act: -0.1700
Data Index: 437355 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6880. Min Act: -0.1700
Data Index: 5998049 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6568. Min Act: -0.1700
Data Index: 5346609 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0005. Min Range: -5.0005
Max Act: 4.6568. Min Act: -0.1700
Data Index: 6046100 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19