Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.9442. Min Act: -0.1700
Data Index: 7110253 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6942. Min Act: -0.1700
Data Index: 7648847 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6630. Min Act: -0.1700
Data Index: 2526641 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6317. Min Act: -0.1700
Data Index: 660815 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6317. Min Act: -0.1700
Data Index: 4956133 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6317. Min Act: -0.1700
Data Index: 7356135 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.5692. Min Act: -0.1700
Data Index: 1005507 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6005. Min Act: -0.1700
Data Index: 4755435 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.6317. Min Act: -0.1700
Data Index: 5633395 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.5380. Min Act: -0.1700
Data Index: 67205 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.5380. Min Act: -0.1700
Data Index: 3777482 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4755. Min Act: -0.1700
Data Index: 2904873 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4442. Min Act: -0.1700
Data Index: 2631965 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4755. Min Act: -0.1700
Data Index: 99851 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4755. Min Act: -0.1700
Data Index: 7572294 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4442. Min Act: -0.1700
Data Index: 1120063 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4442. Min Act: -0.1700
Data Index: 6518033 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4442. Min Act: -0.1700
Data Index: 4990597 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.4130. Min Act: -0.1700
Data Index: 6620906 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9442. Min Range: -6.9442
Max Act: 6.3817. Min Act: -0.1700
Data Index: 4064477 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19