Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4972 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.5074. Min Act: -0.1700
Data Index: 7305620 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.5074. Min Act: -0.1700
Data Index: 7368911 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.5074. Min Act: -0.1700
Data Index: 5342484 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4449. Min Act: -0.1700
Data Index: 909717 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4762. Min Act: -0.1700
Data Index: 7368912 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4762. Min Act: -0.1700
Data Index: 5181164 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4449. Min Act: -0.1700
Data Index: 2793192 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4449. Min Act: -0.1700
Data Index: 387535 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4449. Min Act: -0.1700
Data Index: 3037794 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4449. Min Act: -0.1700
Data Index: 909715 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4137. Min Act: -0.1700
Data Index: 5613281 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4137. Min Act: -0.1700
Data Index: 2541673 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4449. Min Act: -0.1700
Data Index: 2054568 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4137. Min Act: -0.1700
Data Index: 7382079 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.4137. Min Act: -0.1700
Data Index: 5690417 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.3824. Min Act: -0.1700
Data Index: 8569498 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.3824. Min Act: -0.1700
Data Index: 1525270 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.3824. Min Act: -0.1700
Data Index: 3234615 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.3512. Min Act: -0.1700
Data Index: 1565180 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5074. Min Range: -5.5074
Max Act: 5.3512. Min Act: -0.1700
Data Index: 4507878 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19