Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5043 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.8300. Min Act: -0.1700
Data Index: 3239771 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.7987. Min Act: -0.1700
Data Index: 6210422 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.7987. Min Act: -0.1700
Data Index: 674781 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5799. Min Act: -0.1700
Data Index: 5923907 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5799. Min Act: -0.1700
Data Index: 939131 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5799. Min Act: -0.1700
Data Index: 6727391 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.5487. Min Act: -0.1700
Data Index: 2075344 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.4862. Min Act: -0.1700
Data Index: 6070255 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.4549. Min Act: -0.1700
Data Index: 1101375 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.4237. Min Act: -0.1700
Data Index: 939136 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.4237. Min Act: -0.1700
Data Index: 4529762 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3924. Min Act: -0.1700
Data Index: 4440028 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3924. Min Act: -0.1700
Data Index: 2419377 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3924. Min Act: -0.1700
Data Index: 3168600 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3299. Min Act: -0.1700
Data Index: 8417637 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3612. Min Act: -0.1700
Data Index: 7589882 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3299. Min Act: -0.1700
Data Index: 2196827 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3612. Min Act: -0.1700
Data Index: 8218057 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.3612. Min Act: -0.1700
Data Index: 901198 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8300. Min Range: -4.8300
Max Act: 4.2987. Min Act: -0.1700
Data Index: 2867736 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19