Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0205. Min Range: -6.0205
Max Act: 6.0205. Min Act: -0.1700
Data Index: 7090324 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4271628 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2309483 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.7392. Min Act: -0.1700
Data Index: 5142328 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.7080. Min Act: -0.1700
Data Index: 8808832 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6767. Min Act: -0.1700
Data Index: 7025873 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6455. Min Act: -0.1700
Data Index: 177701 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6142. Min Act: -0.1700
Data Index: 7090327 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6142. Min Act: -0.1700
Data Index: 5204069 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6142. Min Act: -0.1700
Data Index: 2524657 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6142. Min Act: -0.1700
Data Index: 8532923 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.5517. Min Act: -0.1700
Data Index: 7389035 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.6142. Min Act: -0.1700
Data Index: 5855779 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.5517. Min Act: -0.1700
Data Index: 6503948 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.5517. Min Act: -0.1700
Data Index: 1425374 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.5205. Min Act: -0.1700
Data Index: 687041 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.5205. Min Act: -0.1700
Data Index: 3058497 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.4892. Min Act: -0.1700
Data Index: 8202707 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7500778 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0205. Min Range: -6.0205
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1386173 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19