Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1102. Min Range: -6.1102
Max Act: 6.1102. Min Act: -0.1700
Data Index: 571181 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.9227. Min Act: -0.1700
Data Index: 1021064 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.8602. Min Act: -0.1700
Data Index: 2804949 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.8290. Min Act: -0.1700
Data Index: 5625338 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.8290. Min Act: -0.1700
Data Index: 8562590 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7665. Min Act: -0.1700
Data Index: 1096462 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7665. Min Act: -0.1700
Data Index: 875022 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7352. Min Act: -0.1699
Data Index: 7867314 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7352. Min Act: -0.1700
Data Index: 8759900 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7352. Min Act: -0.1700
Data Index: 2335466 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7352. Min Act: -0.1700
Data Index: 7460660 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7040. Min Act: -0.1700
Data Index: 5597437 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7040. Min Act: -0.1700
Data Index: 1463478 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7352. Min Act: -0.1700
Data Index: 7601744 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7040. Min Act: -0.1700
Data Index: 5844315 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7040. Min Act: -0.1700
Data Index: 4721000 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.7040. Min Act: -0.1700
Data Index: 7396410 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.6727. Min Act: -0.1700
Data Index: 4064165 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.6727. Min Act: -0.1700
Data Index: 3499986 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1102. Min Range: -6.1102
Max Act: 5.6727. Min Act: -0.1700
Data Index: 5853117 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19