Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4343 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.2233. Min Act: -0.1700
Data Index: 2838819 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1761. Min Act: -0.1700
Data Index: 1310104 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1447. Min Act: -0.1700
Data Index: 3126263 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1289. Min Act: -0.1700
Data Index: 2668044 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1447. Min Act: -0.1700
Data Index: 356265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1289. Min Act: -0.1700
Data Index: 3916523 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 562767 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 8518005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 8141264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 7936622 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 7623443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 6922821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.0974. Min Act: -0.1700
Data Index: 5732438 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 5614213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 5481418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 5412491 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 1915727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 403173 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.0974. Min Act: -0.1700
Data Index: 225946 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2233. Min Range: -3.2233
Max Act: 3.1132. Min Act: -0.1700
Data Index: 2320791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19