Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5378 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5345. Min Range: -11.5345
Max Act: 11.5345. Min Act: -0.1700
Data Index: 1403550 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5345. Min Range: -11.5345
Max Act: 11.4095. Min Act: -0.1700
Data Index: 2976586 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5345. Min Range: -11.5345
Max Act: 11.2220. Min Act: -0.1700
Data Index: 1745822 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5345. Min Range: -11.5345
Max Act: 11.0345. Min Act: -0.1700
Data Index: 786472 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5345. Min Range: -11.5345
Max Act: 11.0345. Min Act: -0.1700
Data Index: 6100988 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.8470. Min Act: -0.1700
Data Index: 290077 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7845. Min Act: -0.1700
Data Index: 77288 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7220. Min Act: -0.1700
Data Index: 1544077 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7845. Min Act: -0.1700
Data Index: 4257108 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7845. Min Act: -0.1700
Data Index: 922925 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7220. Min Act: -0.1700
Data Index: 5555059 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7845. Min Act: -0.1700
Data Index: 4760626 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7220. Min Act: -0.1700
Data Index: 724292 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.7220. Min Act: -0.1700
Data Index: 5969951 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.6595. Min Act: -0.1700
Data Index: 1532579 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.5970. Min Act: -0.1700
Data Index: 71377 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.5970. Min Act: -0.1700
Data Index: 5900772 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.5970. Min Act: -0.1700
Data Index: 6914717 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.5970. Min Act: -0.1700
Data Index: 1404669 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5345. Min Range: -11.5345
Max Act: 10.4720. Min Act: -0.1700
Data Index: 5610525 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19