Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2427 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.6996. Min Act: -0.1700
Data Index: 3997894 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.6371. Min Act: -0.1700
Data Index: 8791677 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.5433. Min Act: -0.1700
Data Index: 6534549 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.4183. Min Act: -0.1700
Data Index: 1430435 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.4496. Min Act: -0.1700
Data Index: 4435691 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.4183. Min Act: -0.1700
Data Index: 6903207 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.3871. Min Act: -0.1700
Data Index: 6094374 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.3558. Min Act: -0.1700
Data Index: 1196409 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.3246. Min Act: -0.1700
Data Index: 6728038 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2933. Min Act: -0.1700
Data Index: 7051862 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2621. Min Act: -0.1700
Data Index: 483227 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2621. Min Act: -0.1700
Data Index: 8464951 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2621. Min Act: -0.1700
Data Index: 6141135 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2308. Min Act: -0.1700
Data Index: 6037270 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2308. Min Act: -0.1700
Data Index: 2477394 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.1683. Min Act: -0.1700
Data Index: 4567528 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.1996. Min Act: -0.1700
Data Index: 5322102 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.2308. Min Act: -0.1700
Data Index: 8367780 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.1996. Min Act: -0.1700
Data Index: 1914956 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6996. Min Range: -6.6996
Max Act: 6.1996. Min Act: -0.1700
Data Index: 3974368 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19