Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3508. Min Range: -6.3508
Max Act: 6.3508. Min Act: -0.1700
Data Index: 5605313 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.7883. Min Act: -0.1700
Data Index: 7202376 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.7883. Min Act: -0.1700
Data Index: 7202379 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.7258. Min Act: -0.1700
Data Index: 7202375 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.7258. Min Act: -0.1700
Data Index: 7202374 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.6633. Min Act: -0.1700
Data Index: 2571575 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.6321. Min Act: -0.1700
Data Index: 7202378 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.6008. Min Act: -0.1700
Data Index: 7202380 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5696. Min Act: -0.1700
Data Index: 5610309 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5696. Min Act: -0.1700
Data Index: 7202377 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5696. Min Act: -0.1700
Data Index: 4811747 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5696. Min Act: -0.1700
Data Index: 5379626 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5383. Min Act: -0.1700
Data Index: 6670868 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5383. Min Act: -0.1700
Data Index: 7202373 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5383. Min Act: -0.1700
Data Index: 1700976 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.5071. Min Act: -0.1700
Data Index: 5557469 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.4758. Min Act: -0.1700
Data Index: 531058 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.4758. Min Act: -0.1700
Data Index: 4793284 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.4758. Min Act: -0.1700
Data Index: 69457 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3508. Min Range: -6.3508
Max Act: 5.4758. Min Act: -0.1700
Data Index: 5307173 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19