Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.8221. Min Act: -0.1700
Data Index: 6324079 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.6971. Min Act: -0.1700
Data Index: 6211433 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.6346. Min Act: -0.1700
Data Index: 6788038 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.6346. Min Act: -0.1700
Data Index: 4135221 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.6346. Min Act: -0.1700
Data Index: 2526954 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.5721. Min Act: -0.1700
Data Index: 5242270 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.5096. Min Act: -0.1700
Data Index: 3004223 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.4471. Min Act: -0.1700
Data Index: 1942085 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.3846. Min Act: -0.1700
Data Index: 7595901 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.3846. Min Act: -0.1700
Data Index: 7019280 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.3221. Min Act: -0.1700
Data Index: 8510125 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.1971. Min Act: -0.1700
Data Index: 1919879 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.1971. Min Act: -0.1700
Data Index: 6340254 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.1971. Min Act: -0.1700
Data Index: 1308796 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.1971. Min Act: -0.1700
Data Index: 6791283 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.1971. Min Act: -0.1700
Data Index: 7201226 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.0721. Min Act: -0.1700
Data Index: 2519641 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.1346. Min Act: -0.1700
Data Index: 349371 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.0721. Min Act: -0.1700
Data Index: 347190 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8221. Min Range: -13.8221
Max Act: 13.0721. Min Act: -0.1700
Data Index: 7040427 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19