Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.7595. Min Act: -0.1700
Data Index: 5606628 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.6657. Min Act: -0.1700
Data Index: 4826055 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.5720. Min Act: -0.1700
Data Index: 6541210 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.4157. Min Act: -0.1700
Data Index: 3895006 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.3220. Min Act: -0.1700
Data Index: 8780189 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.3220. Min Act: -0.1700
Data Index: 1854463 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.2595. Min Act: -0.1700
Data Index: 2416380 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.2595. Min Act: -0.1700
Data Index: 2670497 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.1032. Min Act: -0.1700
Data Index: 8563981 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.0407. Min Act: -0.1700
Data Index: 161020 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7595. Min Range: -6.7595
Max Act: 6.0095. Min Act: -0.1700
Data Index: 4114469 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.9782. Min Act: -0.1700
Data Index: 6024554 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.9782. Min Act: -0.1700
Data Index: 5030474 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.9470. Min Act: -0.1700
Data Index: 1753799 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.9157. Min Act: -0.1700
Data Index: 1353537 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.8845. Min Act: -0.1700
Data Index: 4910130 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.8532. Min Act: -0.1700
Data Index: 7236496 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.8532. Min Act: -0.1700
Data Index: 1752908 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.8532. Min Act: -0.1700
Data Index: 3215995 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7595. Min Range: -6.7595
Max Act: 5.8220. Min Act: -0.1700
Data Index: 5954466 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19