Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0843. Min Range: -6.0843
Max Act: 6.0843. Min Act: -0.1700
Data Index: 6379459 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8655. Min Act: -0.1700
Data Index: 3439657 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8343. Min Act: -0.1700
Data Index: 4742343 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8030. Min Act: -0.1700
Data Index: 3208938 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7718. Min Act: -0.1700
Data Index: 6851863 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7718. Min Act: -0.1699
Data Index: 7544244 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7405. Min Act: -0.1700
Data Index: 749484 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7405. Min Act: -0.1700
Data Index: 1205828 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7093. Min Act: -0.1700
Data Index: 3258169 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7093. Min Act: -0.1700
Data Index: 2887027 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7093. Min Act: -0.1700
Data Index: 6238572 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4295192 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.7093. Min Act: -0.1700
Data Index: 347610 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.6780. Min Act: -0.1700
Data Index: 4056565 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.6780. Min Act: -0.1700
Data Index: 2586397 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.6468. Min Act: -0.1700
Data Index: 6379460 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.6468. Min Act: -0.1700
Data Index: 4056566 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.6468. Min Act: -0.1700
Data Index: 7538315 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.5843. Min Act: -0.1700
Data Index: 8016241 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.6155. Min Act: -0.1700
Data Index: 8073008 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19