Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.9929. Min Act: -0.1700
Data Index: 629670 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0242. Min Range: -7.0242
Max Act: 7.0242. Min Act: -0.1700
Data Index: 6306703 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.8992. Min Act: -0.1700
Data Index: 5478594 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.8054. Min Act: -0.1700
Data Index: 6105164 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.7429. Min Act: -0.1700
Data Index: 5865434 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.7117. Min Act: -0.1700
Data Index: 3109884 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.6804. Min Act: -0.1700
Data Index: 4443085 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.6179. Min Act: -0.1700
Data Index: 2670173 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.6492. Min Act: -0.1700
Data Index: 672411 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5554. Min Act: -0.1700
Data Index: 761324 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5867. Min Act: -0.1700
Data Index: 8001398 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5554. Min Act: -0.1700
Data Index: 8678565 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5554. Min Act: -0.1700
Data Index: 6292185 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5867. Min Act: -0.1700
Data Index: 2867029 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5554. Min Act: -0.1700
Data Index: 6989293 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5554. Min Act: -0.1700
Data Index: 4092540 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5554. Min Act: -0.1700
Data Index: 5079465 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5242. Min Act: -0.1700
Data Index: 2096300 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5242. Min Act: -0.1700
Data Index: 2445764 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0242. Min Range: -7.0242
Max Act: 6.5242. Min Act: -0.1700
Data Index: 1890949 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19