Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2322. Min Range: -6.2322
Max Act: 6.2322. Min Act: -0.1700
Data Index: 4232311 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2322. Min Range: -6.2322
Max Act: 6.0447. Min Act: -0.1700
Data Index: 5744669 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2322. Min Range: -6.2322
Max Act: 6.0447. Min Act: -0.1700
Data Index: 4082402 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.9822. Min Act: -0.1700
Data Index: 8418054 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.9509. Min Act: -0.1700
Data Index: 5054846 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8884. Min Act: -0.1700
Data Index: 1250469 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8884. Min Act: -0.1700
Data Index: 7925413 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8884. Min Act: -0.1700
Data Index: 4097167 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8572. Min Act: -0.1700
Data Index: 4459730 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8572. Min Act: -0.1700
Data Index: 1729852 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8572. Min Act: -0.1700
Data Index: 4201208 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.8259. Min Act: -0.1700
Data Index: 2246611 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7947. Min Act: -0.1700
Data Index: 8520969 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 2489638 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 4718143 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 1545500 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 317852 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 1185983 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 3368893 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 4681262 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19