Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0385. Min Range: -2.0385
Max Act: 2.0385. Min Act: -0.1700
Data Index: 4343798 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0385. Min Range: -2.0385
Max Act: 2.0217. Min Act: -0.1700
Data Index: 1175607 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9540. Min Act: -0.1700
Data Index: 4579504 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9540. Min Act: -0.1700
Data Index: 3945491 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9370. Min Act: -0.1700
Data Index: 1081143 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 4605597 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 175218 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 1907709 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 6322381 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 1175608 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 1175604 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.9030. Min Act: -0.1700
Data Index: 4219348 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8688. Min Act: -0.1700
Data Index: 6004304 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8517. Min Act: -0.1700
Data Index: 1258774 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8517. Min Act: -0.1700
Data Index: 1175601 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8517. Min Act: -0.1700
Data Index: 188851 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8346. Min Act: -0.1700
Data Index: 3462553 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8517. Min Act: -0.1700
Data Index: 4456622 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8174. Min Act: -0.1700
Data Index: 4065379 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0385. Min Range: -2.0385
Max Act: 1.8517. Min Act: -0.1700
Data Index: 4967628 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19