Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.6781. Min Act: -0.1700
Data Index: 3493107 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.6156. Min Act: -0.1700
Data Index: 2572621 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5531. Min Act: -0.1700
Data Index: 537723 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5531. Min Act: -0.1700
Data Index: 7304625 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5219. Min Act: -0.1700
Data Index: 797934 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5531. Min Act: -0.1700
Data Index: 259090 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5219. Min Act: -0.1700
Data Index: 8313114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5219. Min Act: -0.1700
Data Index: 5606033 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5219. Min Act: -0.1700
Data Index: 7796343 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5219. Min Act: -0.1700
Data Index: 2196065 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.5219. Min Act: -0.1700
Data Index: 3470779 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 4718223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 7305338 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 7956796 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4594. Min Act: -0.1700
Data Index: 4609356 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 6468053 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 945664 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4594. Min Act: -0.1700
Data Index: 3601671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 6695440 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6781. Min Range: -5.6781
Max Act: 5.4906. Min Act: -0.1700
Data Index: 1774107 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19