Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.8834. Min Act: -0.1700
Data Index: 7739846 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.7897. Min Act: -0.1700
Data Index: 2785293 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.7897. Min Act: -0.1700
Data Index: 1798591 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.7584. Min Act: -0.1700
Data Index: 6539077 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.6647. Min Act: -0.1700
Data Index: 3533186 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.6647. Min Act: -0.1700
Data Index: 7672320 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.6022. Min Act: -0.1700
Data Index: 8068280 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.6022. Min Act: -0.1700
Data Index: 7304706 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.5709. Min Act: -0.1700
Data Index: 6157267 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.5397. Min Act: -0.1700
Data Index: 3103684 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.5084. Min Act: -0.1700
Data Index: 959869 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.4459. Min Act: -0.1700
Data Index: 536506 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.4459. Min Act: -0.1700
Data Index: 8810579 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.4147. Min Act: -0.1700
Data Index: 2201922 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.4147. Min Act: -0.1700
Data Index: 668323 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.4147. Min Act: -0.1700
Data Index: 5465262 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.3834. Min Act: -0.1700
Data Index: 2584792 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.3834. Min Act: -0.1700
Data Index: 6030929 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.3834. Min Act: -0.1700
Data Index: 2642994 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8834. Min Range: -6.8834
Max Act: 6.3834. Min Act: -0.1700
Data Index: 3397519 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19