Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.9260. Min Act: -0.1700
Data Index: 5702709 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.8635. Min Act: -0.1700
Data Index: 4524711 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.8010. Min Act: -0.1700
Data Index: 7931342 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.6135. Min Act: -0.1700
Data Index: 7999954 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.6135. Min Act: -0.1700
Data Index: 2701035 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.5510. Min Act: -0.1700
Data Index: 5938454 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.4260. Min Act: -0.1700
Data Index: 1025230 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.4260. Min Act: -0.1700
Data Index: 3262663 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.3635. Min Act: -0.1700
Data Index: 8149137 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.2385. Min Act: -0.1700
Data Index: 3966081 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.1760. Min Act: -0.1700
Data Index: 5960752 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.1135. Min Act: -0.1700
Data Index: 3617458 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.0822. Min Act: -0.1700
Data Index: 6393172 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.0822. Min Act: -0.1700
Data Index: 4499348 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.0510. Min Act: -0.1700
Data Index: 7614376 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.0510. Min Act: -0.1700
Data Index: 2488226 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.0197. Min Act: -0.1700
Data Index: 8047196 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9260. Min Range: -8.9260
Max Act: 8.0197. Min Act: -0.1700
Data Index: 345447 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9260. Min Range: -8.9260
Max Act: 7.9885. Min Act: -0.1700
Data Index: 7214535 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9260. Min Range: -8.9260
Max Act: 7.9260. Min Act: -0.1700
Data Index: 165222 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19