Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5834 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.9412. Min Act: -0.1700
Data Index: 5528930 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.8162. Min Act: -0.1700
Data Index: 4911659 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.7224. Min Act: -0.1700
Data Index: 5444879 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.6912. Min Act: -0.1700
Data Index: 28503 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.6599. Min Act: -0.1700
Data Index: 6545573 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.6287. Min Act: -0.1700
Data Index: 2471149 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.6287. Min Act: -0.1700
Data Index: 6382044 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.5662. Min Act: -0.1700
Data Index: 917715 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.5349. Min Act: -0.1700
Data Index: 2589550 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4724. Min Act: -0.1700
Data Index: 2362803 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 7237082 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4724. Min Act: -0.1700
Data Index: 7970024 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 5308904 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 5612468 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 5482714 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 3736221 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 8029393 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4412. Min Act: -0.1700
Data Index: 123249 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4099. Min Act: -0.1700
Data Index: 71918 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9412. Min Range: -5.9412
Max Act: 5.4099. Min Act: -0.1700
Data Index: 1331034 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19