Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2013 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.2310. Min Act: -0.1700
Data Index: 7761436 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.2622. Min Act: -0.1700
Data Index: 514669 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.1685. Min Act: -0.1700
Data Index: 3926863 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.1060. Min Act: -0.1700
Data Index: 5473707 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.0747. Min Act: -0.1700
Data Index: 6305906 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.1372. Min Act: -0.1700
Data Index: 8289210 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.0747. Min Act: -0.1700
Data Index: 2164194 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2622. Min Range: -7.2622
Max Act: 7.0122. Min Act: -0.1700
Data Index: 4832756 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.9497. Min Act: -0.1700
Data Index: 4346585 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.9497. Min Act: -0.1700
Data Index: 8641426 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.9185. Min Act: -0.1700
Data Index: 3425478 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.8247. Min Act: -0.1700
Data Index: 3429640 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.8247. Min Act: -0.1700
Data Index: 6372591 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.8247. Min Act: -0.1700
Data Index: 13828 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.8247. Min Act: -0.1700
Data Index: 3023447 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.7935. Min Act: -0.1700
Data Index: 6375665 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.7935. Min Act: -0.1700
Data Index: 7601726 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.7622. Min Act: -0.1700
Data Index: 1478925 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.7622. Min Act: -0.1700
Data Index: 5823629 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2622. Min Range: -7.2622
Max Act: 6.7310. Min Act: -0.1700
Data Index: 6700359 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19