Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2393 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.3155. Min Act: -0.1700
Data Index: 4700872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.3155. Min Act: -0.1700
Data Index: 5464218 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2842. Min Act: -0.1700
Data Index: 2511899 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 7645867 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 1072075 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 2289795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 4306832 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 87214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 2454215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 5514492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2530. Min Act: -0.1700
Data Index: 5040948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 483062 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 7588540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 727042 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 7000602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 3085217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 3438897 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 3865316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 3538419 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3155. Min Range: -4.3155
Max Act: 4.2217. Min Act: -0.1700
Data Index: 3517629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19