Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9512. Min Act: -0.1700
Data Index: 5616905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9512. Min Act: -0.1700
Data Index: 7085324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 3559387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 8078441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9512. Min Act: -0.1700
Data Index: 8156059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 2149790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 8731804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 8519736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.8886. Min Act: -0.1700
Data Index: 304416 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 3601285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 1034993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 2467665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 8286566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 4794251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 7776437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.8886. Min Act: -0.1700
Data Index: 4543093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 7007334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 6273313 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 6093100 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9512. Min Range: -3.9512
Max Act: 3.9199. Min Act: -0.1700
Data Index: 5898963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19