Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 654 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.9987. Min Act: -0.1700
Data Index: 1022781 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.9675. Min Act: -0.1700
Data Index: 8638333 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.9362. Min Act: -0.1700
Data Index: 6949219 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.8425. Min Act: -0.1700
Data Index: 682945 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.8425. Min Act: -0.1700
Data Index: 3754222 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.7800. Min Act: -0.1700
Data Index: 1805192 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6862. Min Act: -0.1700
Data Index: 7470955 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6862. Min Act: -0.1700
Data Index: 5842624 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6862. Min Act: -0.1700
Data Index: 5468990 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6550. Min Act: -0.1700
Data Index: 1173268 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6550. Min Act: -0.1700
Data Index: 4529293 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6862. Min Act: -0.1700
Data Index: 7199749 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.6237. Min Act: -0.1700
Data Index: 3523430 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5925. Min Act: -0.1700
Data Index: 2819935 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5925. Min Act: -0.1700
Data Index: 6229720 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5925. Min Act: -0.1700
Data Index: 5469010 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5612. Min Act: -0.1700
Data Index: 2746197 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5612. Min Act: -0.1700
Data Index: 3967372 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5612. Min Act: -0.1700
Data Index: 1589471 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9987. Min Range: -7.9987
Max Act: 7.5612. Min Act: -0.1700
Data Index: 4016308 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19