Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1350 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.8284. Min Act: -0.1700
Data Index: 6423960 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7659. Min Act: -0.1700
Data Index: 7126496 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 81709 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 1623785 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 5209947 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6721. Min Act: -0.1700
Data Index: 3472402 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6721. Min Act: -0.1700
Data Index: 2573595 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.7034. Min Act: -0.1700
Data Index: 8760032 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6409. Min Act: -0.1700
Data Index: 4918069 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.6096. Min Act: -0.1700
Data Index: 6036986 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5784. Min Act: -0.1700
Data Index: 5724350 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5471. Min Act: -0.1700
Data Index: 5426140 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 1823675 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 2144014 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4846. Min Act: -0.1700
Data Index: 5487193 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.5159. Min Act: -0.1700
Data Index: 6874116 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4846. Min Act: -0.1700
Data Index: 3770139 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4846. Min Act: -0.1700
Data Index: 1458671 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4846. Min Act: -0.1700
Data Index: 7230262 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8284. Min Range: -6.8284
Max Act: 6.4534. Min Act: -0.1700
Data Index: 5257074 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19