Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1269. Min Range: -5.1269
Max Act: 5.1269. Min Act: -0.1700
Data Index: 788372 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.8456. Min Act: -0.1700
Data Index: 2468338 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.7831. Min Act: -0.1700
Data Index: 4901632 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.7206. Min Act: -0.1700
Data Index: 7113571 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.7519. Min Act: -0.1700
Data Index: 4718000 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.7519. Min Act: -0.1700
Data Index: 7135697 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.7519. Min Act: -0.1700
Data Index: 2013899 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.7206. Min Act: -0.1700
Data Index: 658732 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2725225 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2627389 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 7969508 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 5753317 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 931221 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6581. Min Act: -0.1700
Data Index: 3298439 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 4456923 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6894. Min Act: -0.1700
Data Index: 2437300 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6269. Min Act: -0.1700
Data Index: 4210455 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.6581. Min Act: -0.1700
Data Index: 1059815 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.5956. Min Act: -0.1700
Data Index: 3029193 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1269. Min Range: -5.1269
Max Act: 4.5956. Min Act: -0.1700
Data Index: 4107688 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19