Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0418. Min Range: -7.0418
Max Act: 7.0418. Min Act: -0.1700
Data Index: 6727422 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.9793. Min Act: -0.1700
Data Index: 650846 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.9481. Min Act: -0.1700
Data Index: 6060103 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.9168. Min Act: -0.1700
Data Index: 4955581 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.8231. Min Act: -0.1700
Data Index: 3939045 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.8231. Min Act: -0.1700
Data Index: 5974801 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.7606. Min Act: -0.1700
Data Index: 7560370 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.7293. Min Act: -0.1700
Data Index: 7728876 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.7293. Min Act: -0.1700
Data Index: 7150309 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.7293. Min Act: -0.1700
Data Index: 2331767 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 4828812 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 6785699 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6668. Min Act: -0.1700
Data Index: 92562 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6981. Min Act: -0.1700
Data Index: 3782322 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6668. Min Act: -0.1700
Data Index: 6530277 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6668. Min Act: -0.1700
Data Index: 2778759 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6356. Min Act: -0.1700
Data Index: 5769300 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6043. Min Act: -0.1700
Data Index: 742797 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6043. Min Act: -0.1700
Data Index: 6373903 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.6356. Min Act: -0.1700
Data Index: 1783615 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19