Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2102 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0616. Min Range: -8.0616
Max Act: 8.0616. Min Act: -0.1700
Data Index: 8458305 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0616. Min Range: -8.0616
Max Act: 8.0616. Min Act: -0.1700
Data Index: 6438588 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.9991. Min Act: -0.1700
Data Index: 30709 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.9991. Min Act: -0.1700
Data Index: 5698389 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.9366. Min Act: -0.1700
Data Index: 1104162 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.9366. Min Act: -0.1700
Data Index: 5573325 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.9366. Min Act: -0.1700
Data Index: 6418654 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.8741. Min Act: -0.1700
Data Index: 7829479 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.8116. Min Act: -0.1700
Data Index: 6376968 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.8116. Min Act: -0.1700
Data Index: 2985234 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.8116. Min Act: -0.1700
Data Index: 4546613 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.7491. Min Act: -0.1700
Data Index: 5832630 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 8776317 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6866. Min Act: -0.1700
Data Index: 3485258 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 1907755 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 2933803 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 996440 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.5616. Min Act: -0.1700
Data Index: 4013210 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.5616. Min Act: -0.1700
Data Index: 4100287 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.5616. Min Act: -0.1700
Data Index: 4127050 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19