Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.7284. Min Act: -0.1700
Data Index: 6677442 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.4784. Min Act: -0.1700
Data Index: 2069187 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.4471. Min Act: -0.1700
Data Index: 6511540 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.4159. Min Act: -0.1700
Data Index: 823443 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.3534. Min Act: -0.1700
Data Index: 8415167 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.3534. Min Act: -0.1700
Data Index: 8288118 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.2596. Min Act: -0.1700
Data Index: 6077024 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.2284. Min Act: -0.1700
Data Index: 230484 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.2284. Min Act: -0.1700
Data Index: 3366968 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1971. Min Act: -0.1700
Data Index: 3060753 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1971. Min Act: -0.1700
Data Index: 6429236 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1659. Min Act: -0.1700
Data Index: 6914522 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1659. Min Act: -0.1700
Data Index: 4129111 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1346. Min Act: -0.1700
Data Index: 2756663 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1034. Min Act: -0.1700
Data Index: 1284456 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.1034. Min Act: -0.1700
Data Index: 6294965 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.0721. Min Act: -0.1700
Data Index: 4859354 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.0721. Min Act: -0.1700
Data Index: 5160799 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.0721. Min Act: -0.1700
Data Index: 1952015 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7284. Min Range: -6.7284
Max Act: 6.0409. Min Act: -0.1700
Data Index: 7701869 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19