Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3535 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0721. Min Range: -6.0721
Max Act: 6.0721. Min Act: -0.1700
Data Index: 3881375 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0721. Min Range: -6.0721
Max Act: 6.0408. Min Act: -0.1700
Data Index: 3786081 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0721. Min Range: -6.0721
Max Act: 6.0408. Min Act: -0.1700
Data Index: 4210508 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.9783. Min Act: -0.1699
Data Index: 8188460 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0721. Min Range: -6.0721
Max Act: 6.0096. Min Act: -0.1700
Data Index: 8750850 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.9471. Min Act: -0.1700
Data Index: 325182 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.9471. Min Act: -0.1700
Data Index: 7043143 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.9158. Min Act: -0.1700
Data Index: 7236801 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.9158. Min Act: -0.1700
Data Index: 2590334 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.9158. Min Act: -0.1700
Data Index: 1997302 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8846. Min Act: -0.1700
Data Index: 190225 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8846. Min Act: -0.1700
Data Index: 8750853 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8846. Min Act: -0.1700
Data Index: 3537666 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8846. Min Act: -0.1700
Data Index: 2445472 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8533. Min Act: -0.1700
Data Index: 7178877 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8221. Min Act: -0.1700
Data Index: 2685 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8533. Min Act: -0.1700
Data Index: 6735745 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8221. Min Act: -0.1700
Data Index: 7714806 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8533. Min Act: -0.1700
Data Index: 4105384 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0721. Min Range: -6.0721
Max Act: 5.8221. Min Act: -0.1699
Data Index: 5052653 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19