Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.5941. Min Act: -0.1700
Data Index: 6553332 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.5316. Min Act: -0.1700
Data Index: 946912 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.5004. Min Act: -0.1700
Data Index: 6051206 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.4379. Min Act: -0.1700
Data Index: 5758319 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.4066. Min Act: -0.1700
Data Index: 7325613 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3754. Min Act: -0.1700
Data Index: 8325763 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3441. Min Act: -0.1700
Data Index: 5833938 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3754. Min Act: -0.1700
Data Index: 580739 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3441. Min Act: -0.1700
Data Index: 3529363 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3754. Min Act: -0.1700
Data Index: 1878539 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3129. Min Act: -0.1700
Data Index: 7646980 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.3129. Min Act: -0.1700
Data Index: 6423187 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2504. Min Act: -0.1700
Data Index: 5664397 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2816. Min Act: -0.1700
Data Index: 3779289 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2816. Min Act: -0.1700
Data Index: 2330147 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2504. Min Act: -0.1700
Data Index: 7134053 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2504. Min Act: -0.1700
Data Index: 3214842 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2504. Min Act: -0.1700
Data Index: 4936868 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2504. Min Act: -0.1700
Data Index: 7159859 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5941. Min Range: -5.5941
Max Act: 5.2504. Min Act: -0.1700
Data Index: 2043548 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19