Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.6600. Min Act: -0.1700
Data Index: 8177560 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5662. Min Act: -0.1700
Data Index: 4835058 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5350. Min Act: -0.1700
Data Index: 7250953 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6448399 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5350. Min Act: -0.1700
Data Index: 2118410 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4300362 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4544972 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5037. Min Act: -0.1700
Data Index: 8089094 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5037. Min Act: -0.1700
Data Index: 1704560 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4725. Min Act: -0.1700
Data Index: 8177559 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5037. Min Act: -0.1700
Data Index: 5340750 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4725. Min Act: -0.1700
Data Index: 2660369 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.5037. Min Act: -0.1700
Data Index: 7103030 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4725. Min Act: -0.1700
Data Index: 8465752 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4725. Min Act: -0.1700
Data Index: 66032 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4412. Min Act: -0.1700
Data Index: 3246426 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4412. Min Act: -0.1700
Data Index: 1182820 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4412. Min Act: -0.1700
Data Index: 1019497 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4412. Min Act: -0.1700
Data Index: 7469364 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6600. Min Range: -4.6600
Max Act: 4.4412. Min Act: -0.1700
Data Index: 6514551 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19