Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 3530874 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.7571. Min Act: -0.1700
Data Index: 2000929 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.7258. Min Act: -0.1700
Data Index: 7020179 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.6946. Min Act: -0.1700
Data Index: 7119515 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.6321. Min Act: -0.1700
Data Index: 4126601 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.6633. Min Act: -0.1700
Data Index: 1651431 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.6633. Min Act: -0.1700
Data Index: 121214 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.6008. Min Act: -0.1700
Data Index: 4927429 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.6008. Min Act: -0.1700
Data Index: 4197179 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5383. Min Act: -0.1700
Data Index: 5038362 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5696. Min Act: -0.1700
Data Index: 3728087 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5696. Min Act: -0.1700
Data Index: 7376998 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5696. Min Act: -0.1700
Data Index: 2343965 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5383. Min Act: -0.1700
Data Index: 2031221 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5383. Min Act: -0.1700
Data Index: 4990428 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5383. Min Act: -0.1700
Data Index: 5012397 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5696. Min Act: -0.1700
Data Index: 4349435 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5071. Min Act: -0.1700
Data Index: 7070731 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5071. Min Act: -0.1700
Data Index: 6113569 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5071. Min Act: -0.1700
Data Index: 6722485 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19