Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.7397. Min Act: -0.1700
Data Index: 2226222 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.7397. Min Act: -0.1700
Data Index: 511019 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.7085. Min Act: -0.1700
Data Index: 5390917 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.7085. Min Act: -0.1700
Data Index: 989987 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6772. Min Act: -0.1700
Data Index: 767784 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 8825952 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6460. Min Act: -0.1700
Data Index: 1573702 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6460. Min Act: -0.1700
Data Index: 8403914 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6460. Min Act: -0.1700
Data Index: 4367356 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6460. Min Act: -0.1700
Data Index: 5428631 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6772. Min Act: -0.1700
Data Index: 187837 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6460. Min Act: -0.1700
Data Index: 5607368 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 2683829 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.5835. Min Act: -0.1700
Data Index: 363001 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1694
Data Index: 2770801 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 972433 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 989988 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 2165924 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 3531473 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7397. Min Range: -4.7397
Max Act: 4.6147. Min Act: -0.1700
Data Index: 7075743 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19