Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.5000. Min Act: -0.1699
Data Index: 6658115 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.5000. Min Act: -0.1700
Data Index: 308436 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.5000. Min Act: -0.1696
Data Index: 3146607 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4912. Min Act: -0.1700
Data Index: 7044035 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4824. Min Act: -0.1697
Data Index: 3475926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4561. Min Act: -0.1699
Data Index: 2592713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4649. Min Act: -0.1700
Data Index: 7294685 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4297. Min Act: -0.1607
Data Index: 6052662 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4209. Min Act: -0.1700
Data Index: 4657169 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4209. Min Act: -0.1700
Data Index: 4280432 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4209. Min Act: -0.1699
Data Index: 5570899 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4297. Min Act: -0.1700
Data Index: 6963633 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4121. Min Act: -0.1700
Data Index: 4505361 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4121. Min Act: -0.1700
Data Index: 2847654 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4121. Min Act: -0.1700
Data Index: 5184743 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4032. Min Act: -0.1700
Data Index: 5874016 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4032. Min Act: -0.1700
Data Index: 7778776 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4032. Min Act: -0.1699
Data Index: 2006767 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4032. Min Act: -0.1603
Data Index: 5732464 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5000. Min Range: -1.5000
Max Act: 1.4032. Min Act: -0.1700
Data Index: 3020698 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19