Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5236. Min Range: -7.5236
Max Act: 7.5236. Min Act: -0.1700
Data Index: 5441158 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5236. Min Range: -7.5236
Max Act: 7.5236. Min Act: -0.1700
Data Index: 2188017 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5236. Min Range: -7.5236
Max Act: 7.2111. Min Act: -0.1700
Data Index: 7223525 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5236. Min Range: -7.5236
Max Act: 7.0861. Min Act: -0.1700
Data Index: 3868029 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5236. Min Range: -7.5236
Max Act: 7.0549. Min Act: -0.1700
Data Index: 1119287 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5236. Min Range: -7.5236
Max Act: 7.0549. Min Act: -0.1700
Data Index: 1700584 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.9611. Min Act: -0.1700
Data Index: 3575161 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.9924. Min Act: -0.1700
Data Index: 184263 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.9611. Min Act: -0.1700
Data Index: 1741646 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.9299. Min Act: -0.1700
Data Index: 3776391 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.8986. Min Act: -0.1700
Data Index: 5506430 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.8674. Min Act: -0.1700
Data Index: 5410148 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.8361. Min Act: -0.1700
Data Index: 5476820 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.8674. Min Act: -0.1700
Data Index: 110115 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.8049. Min Act: -0.1700
Data Index: 6205673 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.7111. Min Act: -0.1700
Data Index: 2490805 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.7424. Min Act: -0.1700
Data Index: 6659718 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.7424. Min Act: -0.1700
Data Index: 5718256 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.7424. Min Act: -0.1700
Data Index: 8162150 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5236. Min Range: -7.5236
Max Act: 6.6486. Min Act: -0.1700
Data Index: 3042648 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19