Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8951. Min Act: -0.1700
Data Index: 5403503 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.9576. Min Act: -0.1700
Data Index: 4754478 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8326. Min Act: -0.1700
Data Index: 3724357 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8326. Min Act: -0.1700
Data Index: 8360691 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8326. Min Act: -0.1700
Data Index: 7146460 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8013. Min Act: -0.1700
Data Index: 4022208 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8013. Min Act: -0.1700
Data Index: 967851 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.8326. Min Act: -0.1700
Data Index: 388320 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7701. Min Act: -0.1700
Data Index: 4233 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7701. Min Act: -0.1700
Data Index: 6499527 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7701. Min Act: -0.1700
Data Index: 3212453 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7701. Min Act: -0.1700
Data Index: 2923496 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7388. Min Act: -0.1700
Data Index: 7938738 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7388. Min Act: -0.1700
Data Index: 2868479 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7701. Min Act: -0.1700
Data Index: 4713336 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7388. Min Act: -0.1700
Data Index: 3077815 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7076. Min Act: -0.1700
Data Index: 1618578 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7076. Min Act: -0.1700
Data Index: 2878967 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7076. Min Act: -0.1700
Data Index: 5236028 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9576. Min Range: -4.9576
Max Act: 4.7388. Min Act: -0.1700
Data Index: 5248394 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19