Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4214 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2322. Min Range: -10.2322
Max Act: 10.2322. Min Act: -0.1700
Data Index: 7291108 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2322. Min Range: -10.2322
Max Act: 10.1697. Min Act: -0.1700
Data Index: 25373 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2322. Min Range: -10.2322
Max Act: 10.1072. Min Act: -0.1700
Data Index: 1910533 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2322. Min Range: -10.2322
Max Act: 10.1072. Min Act: -0.1700
Data Index: 3177623 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2322. Min Range: -10.2322
Max Act: 10.0447. Min Act: -0.1700
Data Index: 2529031 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.9822. Min Act: -0.1700
Data Index: 5045232 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.9197. Min Act: -0.1700
Data Index: 6213637 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.9197. Min Act: -0.1700
Data Index: 1823862 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.9197. Min Act: -0.1700
Data Index: 5672555 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.8572. Min Act: -0.1700
Data Index: 6873520 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.8572. Min Act: -0.1700
Data Index: 1984879 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.8572. Min Act: -0.1700
Data Index: 66965 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.8572. Min Act: -0.1700
Data Index: 1164899 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 6253095 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 5570753 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 958068 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 5541980 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 2204006 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 4994647 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2322. Min Range: -10.2322
Max Act: 9.7947. Min Act: -0.1700
Data Index: 4973941 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19