Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.3658. Min Act: -0.1700
Data Index: 169365 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.3346. Min Act: -0.1700
Data Index: 5844391 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.2721. Min Act: -0.1700
Data Index: 5449405 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.1783. Min Act: -0.1700
Data Index: 5008669 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.1471. Min Act: -0.1700
Data Index: 1413215 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.1471. Min Act: -0.1700
Data Index: 5864537 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.1158. Min Act: -0.1700
Data Index: 7331880 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.0533. Min Act: -0.1700
Data Index: 4918059 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.0221. Min Act: -0.1700
Data Index: 324359 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3658. Min Range: -7.3658
Max Act: 7.0221. Min Act: -0.1700
Data Index: 1960611 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.9908. Min Act: -0.1700
Data Index: 5052516 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.9908. Min Act: -0.1700
Data Index: 5737595 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.9596. Min Act: -0.1700
Data Index: 4462968 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.9283. Min Act: -0.1700
Data Index: 8089927 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.9283. Min Act: -0.1700
Data Index: 266034 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.8658. Min Act: -0.1700
Data Index: 4255956 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.8658. Min Act: -0.1700
Data Index: 4290373 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.8658. Min Act: -0.1700
Data Index: 1509997 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.8033. Min Act: -0.1700
Data Index: 1220571 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3658. Min Range: -7.3658
Max Act: 6.8033. Min Act: -0.1700
Data Index: 5176515 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19