Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 742 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4219926 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.7266. Min Act: -0.1700
Data Index: 8450402 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6953. Min Act: -0.1700
Data Index: 6005690 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6953. Min Act: -0.1700
Data Index: 8801688 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6328. Min Act: -0.1700
Data Index: 3945454 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6641. Min Act: -0.1700
Data Index: 2377731 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6328. Min Act: -0.1700
Data Index: 1668439 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6328. Min Act: -0.1700
Data Index: 8002377 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6328. Min Act: -0.1700
Data Index: 8450401 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6016. Min Act: -0.1700
Data Index: 4008704 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6016. Min Act: -0.1700
Data Index: 6844443 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6016. Min Act: -0.1700
Data Index: 8330627 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.5703. Min Act: -0.1700
Data Index: 8045040 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.5703. Min Act: -0.1700
Data Index: 2426401 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.6016. Min Act: -0.1700
Data Index: 2586328 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.5703. Min Act: -0.1700
Data Index: 5506801 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.5391. Min Act: -0.1700
Data Index: 6260134 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.5391. Min Act: -0.1700
Data Index: 4545948 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.5078. Min Act: -0.1700
Data Index: 4751598 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7578. Min Range: -5.7578
Max Act: 5.4766. Min Act: -0.1700
Data Index: 7517503 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19