Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3481. Min Act: -0.1700
Data Index: 3090939 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2856. Min Act: -0.1700
Data Index: 969790 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2856. Min Act: -0.1700
Data Index: 2579286 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2231. Min Act: -0.1700
Data Index: 7768322 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2231. Min Act: -0.1700
Data Index: 1746209 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1294. Min Act: -0.1700
Data Index: 1264904 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1606. Min Act: -0.1700
Data Index: 6361335 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 4769647 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 6511581 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 5528027 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0669. Min Act: -0.1700
Data Index: 1289657 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0669. Min Act: -0.1700
Data Index: 2116196 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0356. Min Act: -0.1700
Data Index: 250560 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0356. Min Act: -0.1700
Data Index: 3835469 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0044. Min Act: -0.1700
Data Index: 3223530 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0044. Min Act: -0.1700
Data Index: 2739132 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0044. Min Act: -0.1700
Data Index: 5767977 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0044. Min Act: -0.1700
Data Index: 979763 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0044. Min Act: -0.1700
Data Index: 3738910 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9731. Min Act: -0.1700
Data Index: 4542845 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19