Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3039 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3166. Min Range: -8.3166
Max Act: 8.3166. Min Act: -0.1700
Data Index: 3134748 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.7541. Min Act: -0.1700
Data Index: 30444 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.7228. Min Act: -0.1700
Data Index: 4948038 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.5353. Min Act: -0.1700
Data Index: 3987174 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.4728. Min Act: -0.1700
Data Index: 1579346 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.4416. Min Act: -0.1700
Data Index: 5125119 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.3478. Min Act: -0.1700
Data Index: 1465458 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.3478. Min Act: -0.1700
Data Index: 5784864 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.3166. Min Act: -0.1700
Data Index: 5552776 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.3166. Min Act: -0.1700
Data Index: 3255894 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.2228. Min Act: -0.1700
Data Index: 7033823 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.1916. Min Act: -0.1700
Data Index: 854495 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.1916. Min Act: -0.1700
Data Index: 2398495 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 5836515 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 2153025 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 8832264 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 3064929 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.0666. Min Act: -0.1700
Data Index: 1205489 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.0353. Min Act: -0.1700
Data Index: 8703835 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3166. Min Range: -8.3166
Max Act: 7.0353. Min Act: -0.1700
Data Index: 4015872 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19