Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2966. Min Range: -8.2966
Max Act: 8.2966. Min Act: -0.1700
Data Index: 2105128 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.8591. Min Act: -0.1699
Data Index: 4038201 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.6091. Min Act: -0.1700
Data Index: 331119 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.5466. Min Act: -0.1700
Data Index: 2705350 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.5466. Min Act: -0.1700
Data Index: 4172242 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.5466. Min Act: -0.1700
Data Index: 6345899 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.4529. Min Act: -0.1700
Data Index: 113898 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.4529. Min Act: -0.1700
Data Index: 1668260 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.4841. Min Act: -0.1700
Data Index: 6060376 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.3904. Min Act: -0.1700
Data Index: 6957655 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.4216. Min Act: -0.1700
Data Index: 1548428 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.3904. Min Act: -0.1700
Data Index: 1098373 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.3591. Min Act: -0.1700
Data Index: 7114390 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.3279. Min Act: -0.1700
Data Index: 1713208 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.3591. Min Act: -0.1700
Data Index: 8734451 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.3591. Min Act: -0.1700
Data Index: 4330909 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.2966. Min Act: -0.1700
Data Index: 2984449 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.2966. Min Act: -0.1700
Data Index: 453912 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.2654. Min Act: -0.1700
Data Index: 5449140 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2966. Min Range: -8.2966
Max Act: 7.2654. Min Act: -0.1700
Data Index: 1285861 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19