Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.7938. Min Act: -0.1700
Data Index: 1545167 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.5438. Min Act: -0.1700
Data Index: 5484524 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.4188. Min Act: -0.1700
Data Index: 3533715 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.4188. Min Act: -0.1700
Data Index: 8832482 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.3563. Min Act: -0.1700
Data Index: 34487 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.2938. Min Act: -0.1700
Data Index: 2887346 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.3563. Min Act: -0.1700
Data Index: 6547334 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.2313. Min Act: -0.1700
Data Index: 7347389 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.2313. Min Act: -0.1700
Data Index: 3066251 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.2313. Min Act: -0.1700
Data Index: 6857533 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.2313. Min Act: -0.1700
Data Index: 6722069 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.1688. Min Act: -0.1700
Data Index: 4795466 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.1688. Min Act: -0.1700
Data Index: 2280348 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.1688. Min Act: -0.1700
Data Index: 8429697 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.1376. Min Act: -0.1700
Data Index: 6512904 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.0751. Min Act: -0.1700
Data Index: 7659264 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.1063. Min Act: -0.1700
Data Index: 2420954 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.1063. Min Act: -0.1700
Data Index: 8726951 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.0751. Min Act: -0.1700
Data Index: 5880710 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7938. Min Range: -8.7938
Max Act: 8.0751. Min Act: -0.1700
Data Index: 3556192 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19