Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0600. Min Range: -8.0600
Max Act: 8.0600. Min Act: -0.1700
Data Index: 1481496 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.6225. Min Act: -0.1700
Data Index: 791442 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.4663. Min Act: -0.1700
Data Index: 64724 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.4663. Min Act: -0.1700
Data Index: 3451231 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.4350. Min Act: -0.1700
Data Index: 875084 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.3725. Min Act: -0.1700
Data Index: 3653571 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.3100. Min Act: -0.1700
Data Index: 3378467 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.2788. Min Act: -0.1700
Data Index: 7826660 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.2788. Min Act: -0.1700
Data Index: 2745457 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.2163. Min Act: -0.1700
Data Index: 4735399 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.2163. Min Act: -0.1700
Data Index: 5501820 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1850. Min Act: -0.1700
Data Index: 203417 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1850. Min Act: -0.1700
Data Index: 508756 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1538. Min Act: -0.1700
Data Index: 3592508 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1225. Min Act: -0.1700
Data Index: 6468890 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1225. Min Act: -0.1700
Data Index: 6957979 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1225. Min Act: -0.1700
Data Index: 6614781 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.1225. Min Act: -0.1700
Data Index: 5771121 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.0600. Min Act: -0.1700
Data Index: 3640558 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0600. Min Range: -8.0600
Max Act: 7.0600. Min Act: -0.1700
Data Index: 6526975 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19