Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 513 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7922. Min Act: -0.1700
Data Index: 4966570 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7609. Min Act: -0.1700
Data Index: 2292783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7609. Min Act: -0.1700
Data Index: 4293893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7609. Min Act: -0.1700
Data Index: 7394934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7609. Min Act: -0.1700
Data Index: 1965292 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7609. Min Act: -0.1700
Data Index: 178964 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 590769 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 277101 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 455034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 133289 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 120365 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 1149011 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 850027 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 201991 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1699
Data Index: 322295 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 1009470 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 717087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 1093134 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 1084356 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7922. Min Range: -3.7922
Max Act: 3.7296. Min Act: -0.1700
Data Index: 163139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19