Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6114 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.7773. Min Act: -0.1700
Data Index: 7150449 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.7460. Min Act: -0.1700
Data Index: 3432437 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.6523. Min Act: -0.1700
Data Index: 4980740 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.5585. Min Act: -0.1700
Data Index: 40015 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.5273. Min Act: -0.1700
Data Index: 2990334 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.4960. Min Act: -0.1700
Data Index: 2638806 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.4335. Min Act: -0.1700
Data Index: 7749178 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3710. Min Act: -0.1700
Data Index: 6893389 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3398. Min Act: -0.1700
Data Index: 7806071 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3398. Min Act: -0.1700
Data Index: 8395473 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3710. Min Act: -0.1700
Data Index: 7405294 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3398. Min Act: -0.1700
Data Index: 7502907 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3085. Min Act: -0.1700
Data Index: 3170436 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3398. Min Act: -0.1700
Data Index: 2501997 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.3085. Min Act: -0.1700
Data Index: 4827358 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.2773. Min Act: -0.1700
Data Index: 4505028 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.2773. Min Act: -0.1700
Data Index: 116905 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.2460. Min Act: -0.1700
Data Index: 1687481 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.2773. Min Act: -0.1700
Data Index: 4948627 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7773. Min Range: -6.7773
Max Act: 6.2460. Min Act: -0.1700
Data Index: 5781734 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19