Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.5528. Min Act: -0.1700
Data Index: 6768885 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.4278. Min Act: -0.1700
Data Index: 4466430 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.2403. Min Act: -0.1700
Data Index: 1211446 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.2403. Min Act: -0.1700
Data Index: 5532292 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.1466. Min Act: -0.1700
Data Index: 944734 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.1153. Min Act: -0.1700
Data Index: 7415793 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.1466. Min Act: -0.1700
Data Index: 6651195 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.1153. Min Act: -0.1700
Data Index: 4815520 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.1153. Min Act: -0.1700
Data Index: 8115903 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.0841. Min Act: -0.1700
Data Index: 2498964 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.0841. Min Act: -0.1700
Data Index: 262652 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.0216. Min Act: -0.1700
Data Index: 4776010 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9903. Min Act: -0.1700
Data Index: 7434065 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9903. Min Act: -0.1700
Data Index: 8594208 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5528. Min Range: -5.5528
Max Act: 5.0216. Min Act: -0.1700
Data Index: 812792 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9591. Min Act: -0.1700
Data Index: 8143020 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9278. Min Act: -0.1700
Data Index: 8128816 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9591. Min Act: -0.1700
Data Index: 5142880 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9278. Min Act: -0.1700
Data Index: 2807698 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5528. Min Range: -5.5528
Max Act: 4.9278. Min Act: -0.1700
Data Index: 4196936 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19