Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5487. Min Range: -6.5487
Max Act: 6.5487. Min Act: -0.1700
Data Index: 6679679 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5487. Min Range: -6.5487
Max Act: 6.0487. Min Act: -0.1700
Data Index: 2659779 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.9237. Min Act: -0.1700
Data Index: 4668622 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7987. Min Act: -0.1700
Data Index: 1487961 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7987. Min Act: -0.1700
Data Index: 4609683 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7987. Min Act: -0.1700
Data Index: 4091863 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7675. Min Act: -0.1700
Data Index: 4092402 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7050. Min Act: -0.1700
Data Index: 3744810 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7362. Min Act: -0.1700
Data Index: 5408107 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7050. Min Act: -0.1700
Data Index: 2448057 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7050. Min Act: -0.1700
Data Index: 2080895 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.7050. Min Act: -0.1700
Data Index: 5178643 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6737. Min Act: -0.1700
Data Index: 6875034 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 2773636 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 8387337 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6425. Min Act: -0.1700
Data Index: 2581545 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 7797319 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 3165629 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.5800. Min Act: -0.1700
Data Index: 7501798 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5487. Min Range: -6.5487
Max Act: 5.6425. Min Act: -0.1700
Data Index: 2871627 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19