Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5011 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.5230. Min Act: -0.1700
Data Index: 1175813 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.4918. Min Act: -0.1700
Data Index: 5859560 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.4293. Min Act: -0.1700
Data Index: 633093 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.3355. Min Act: -0.1700
Data Index: 3131435 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.2418. Min Act: -0.1700
Data Index: 773692 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.2105. Min Act: -0.1700
Data Index: 5984796 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.1793. Min Act: -0.1700
Data Index: 2284178 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.1480. Min Act: -0.1700
Data Index: 4215881 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.1793. Min Act: -0.1700
Data Index: 4020297 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.1168. Min Act: -0.1700
Data Index: 7173773 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.1168. Min Act: -0.1700
Data Index: 6954606 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.0543. Min Act: -0.1700
Data Index: 5984798 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.0543. Min Act: -0.1700
Data Index: 3103354 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.0230. Min Act: -0.1700
Data Index: 2532641 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.0543. Min Act: -0.1700
Data Index: 8170860 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.0230. Min Act: -0.1700
Data Index: 5823587 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5230. Min Range: -6.5230
Max Act: 6.0230. Min Act: -0.1700
Data Index: 5833505 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5230. Min Range: -6.5230
Max Act: 5.9918. Min Act: -0.1700
Data Index: 1242474 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5230. Min Range: -6.5230
Max Act: 5.9918. Min Act: -0.1700
Data Index: 6145191 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5230. Min Range: -6.5230
Max Act: 5.9918. Min Act: -0.1700
Data Index: 600227 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19