Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5368 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1416. Min Range: -3.1416
Max Act: 3.1416. Min Act: -0.1700
Data Index: 6935417 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1416. Min Range: -3.1416
Max Act: 3.0943. Min Act: -0.1700
Data Index: 7343517 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1416. Min Range: -3.1416
Max Act: 3.0470. Min Act: -0.1700
Data Index: 992660 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1416. Min Range: -3.1416
Max Act: 3.0312. Min Act: -0.1700
Data Index: 7527568 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9996. Min Act: -0.1700
Data Index: 8371718 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9838. Min Act: -0.1700
Data Index: 3997269 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9680. Min Act: -0.1700
Data Index: 6778129 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9680. Min Act: -0.1700
Data Index: 7972043 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9680. Min Act: -0.1700
Data Index: 4300146 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9522. Min Act: -0.1700
Data Index: 992656 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9522. Min Act: -0.1700
Data Index: 2713267 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9522. Min Act: -0.1700
Data Index: 70576 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9363. Min Act: -0.1700
Data Index: 6935419 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9522. Min Act: -0.1700
Data Index: 4675540 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9205. Min Act: -0.1700
Data Index: 1256437 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9522. Min Act: -0.1700
Data Index: 6778132 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9363. Min Act: -0.1700
Data Index: 4476713 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9363. Min Act: -0.1700
Data Index: 8374399 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9363. Min Act: -0.1700
Data Index: 8593763 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1416. Min Range: -3.1416
Max Act: 2.9046. Min Act: -0.1700
Data Index: 382435 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19